Search

Highlights • We present a novel detection method for heart girth measuring position. • We present a novel automated measurement method for heart girth measurement. • The average relative error of our measurement method is 7.87%. Abstract As increasing number of studies for body measurement purposes in both the animal breeding and production stages, several papers have already evaluated the feasibility of consumer depth sensors for linear body measurement of livestock including pigs and cows. However, taking heart girth measurements is one of the major problems in livestock farming and the current studies remain under-evaluated for automated extraction of livestock girth measurements. In this paper, we develop a novel automatic measurement method for pig heart girth from body surface point clouds. Firstly, we preprocess the original point cloud data with methods including segmentation and pose normalization. Secondly, we resort to point cloud cross-section feature to detect the measuring position of the heart girth. Thirdly, the heart girth point clouds is achieved by slicing point cloud on the measuring position. Finally, the length of the heart girth is obtained by approximating the perimeter of the curve fitted by the heart girth point clouds. Experimental results show that the correct detection rate of measuring position of pig heart girth is 96.5% and the average relative error for heart girth from our method is 7.87%, which demonstrates the efficacy of the proposed measurement method. The program of automated calculation of heart girth measurement in pigs using body surface point clouds and its corresponding data set can be downloaded freely from https://github.com/LiveStockShapeAnalysis/Girth-fitting-methods to livestock industry and research. [ABSTRACT FROM AUTHOR]

It remains challenging to estimate a crop’s leaf area profile accurately and automatically. Terrestrial laser scanning (TLS) offers a potential solution, since it has a small footprint and can be used to rapidly and accurately resolve the canopy’s 3D structure. To improve the accuracy of vertical leaf area profile estimation, we selected point clouds from three corn plants scanned in two TLS experiments and used an improved voxel-based leaf area profile estimation method based on Wilson’s contact-frequency theory. The improvement has three aspects: First, it separates corn leaf points from stalk points using the difference-of-normals (DoN) method, which is commonly used to separate different surfaces of manmade objects such as tables or walls. The DoN method captures the geometrical difference between corn leaves and stalks. Second, it determines the optimal voxel size based on the calculated contact frequency. Third, it applies Wilson’s voxel-based contact-frequency method to the LiDAR point clouds. Comparing the estimated and measured leaf area profiles showed that separating leaf and stalk points improved the leaf area accuracy, which depended on the voxel size. The optimal voxel sizes were 10 cm × 10 cm × 10 cm and 5 cm × 5 cm × 5 cm, respectively, in the two study years based on irradiation of the corn plant with a single laser beam. The estimated vertical and cumulative leaf area profiles agreed well with the measured profiles; mean absolute errors for the samples ranged from 15.7 to 18.9%. [ABSTRACT FROM AUTHOR]

Locust swarms are destructive agricultural and biological disasters in China. The green prevention and control (GPC, such as ecological regulation and physical control) of locusts is a comprehensive and complex process, especially in information technology. In this study, a web-based decision support system (DSS) integrated with geographic information system (GIS) is developed to prevent and control locusts efficiently, accurately, and rapidly. The locust prevention and control DSS (LPCDSS) is developed to assist farmers and local government agencies in Chinese provinces with high incidence of locust by providing spatial decision-making information. LPCDSS offers online access to county, city, provincial, and national level data queries and is capable of storing, spatial analyzing, and displaying geographically referenced information of locust data. The system can also provide the real-time tracking of global positioning system (GPS) location, as well as goods scheduling of locust plagues prevention. Six types of web service, real-time data synchronization model, and locust population estimation model are developed and implemented to improve the decision-making usability and feasibility of LPCDSS by adopting a three-layer system architecture. The system is developed by using several programming languages, libraries, and software components. As a result, this system has been running successfully for several years and has improved efficiency of the locust prevention and control in China with high efficiency and great accuracy. The approaches and methodologies presented in this paper can serve as a reference for those who are interested in developing integrated pest control system applications. [ABSTRACT FROM AUTHOR]

We propose an approach for estimating non-rigid correspondences between two shapes that can handle articulation and deformation of the surfaces to be matched. It operates on open or closed surfaces represented by point clouds and, therefore, it can be applied on other representations that can be converted into point clouds. Our method is capable of automatically discovering the articulated parts of the surface without requiring knowledge of the topology or the number of rigid parts. Processing begins by estimating potential sparse correspondences between the source and the target surface. These are used to align the largest corresponding parts of the two surfaces. Fragments of the surface that are not consistent with this alignment generate part hypotheses on which the algorithm is applied recursively. We present qualitative and quantitative results on four datasets comprising open and closed surfaces. [ABSTRACT FROM AUTHOR]

The main objective of this study is to develop a field survey system for land consolidation based on 3S (geographic information system, GIS; Global Positioning System, GPS; and remote sensing, RS) and speech recognition technology. Field survey in land consolidation is a complex and high-tech process. Traditional survey methods are difficult to use in locating, measuring, recording, and other related tasks. Through 3S and speech recognition technology, Android smart phones could address the aforementioned problems by providing a new method of land information collection. In this study, we present a land consolidation field survey system (LCFSS), which is developed on an Android mobile platform and integrates 3S and speech recognition technology to support the field survey of land consolidation. The proposed system is made advantageous by its low cost, high efficiency, portability, and user-friendliness. To improve the usability and feasibility of the LCFSS for decision making, we develop a data-adaptive development model, data compression model, three-parameter model for coordinate registration, and speech processing model. With the Unified Modeling Language, 5 functional modules and more than 16 application cases are described. On the basis of these models, the functions of system management, data import, project survey, coordinate registration, and data output are implemented by adopting the system architecture with four layers. The key achievement is tested and applied to a land consolidation survey in the provinces of Ningxia, Anhui, Shandong, and others. Results show that the efficiency of land information collection and other functions is improved with the use of the proposed system. Therefore, the approaches and methodology presented in this work could serve as a reference for those who are interested in developing mobile system applications based on 3S and speech recognition technology. [ABSTRACT FROM AUTHOR]

Objective: To compare large‐ and medium‐sized choroidal vascularity and the choriocapillaris (CC) flow area in children with different refractive errors using swept‐source optical coherence tomography angiography (SS‐OCTA). Methods: Forty‐two anisometropic children were enrolled and divided into hyperopic anisometropia (HA) and myopic anisometropia (MA) groups. SS‐OCTA was performed to analyse choroidal vascularity. Mean choroidal thickness (CT), choroidal vascularity volume (CVV), choroidal vascularity index (CVI) and CC flow area were compared between the two eyes. The inter‐ocular differences between the two groups were also determined. Results: Mean CT and CVV were highest in eyes with shorter axial lengths in both refractive groups, and the difference between the two eyes was positively correlated with the difference in axial length at the foveal region. Significant differences in the CVI in the MA group were only found in the parafoveal region. Inter‐ocular differences in the CC were significantly reduced in eyes with longer axial lengths in the foveal and parafoveal regions of the HA and MA groups, respectively. Comparing inter‐ocular differences, CC was significantly greater in the parafoveal region of the MA group than the HA group. Conclusions: All layers of choroidal vasculature were thinner in eyes with longer axial lengths in all groups. The inter‐ocular CC difference was greater in the MA than in the HA group, with similar differences in axial length. This suggests that both medium‐to‐large choroidal vascular and choroidal capillaries may play a role in myopia development. [ABSTRACT FROM AUTHOR]

Continuous monitoring of crop growth status using time-series remote sensing image is essential for crop management and yield prediction. The growing season of summer corn in the North China Plain with the period of rain and hot, which makes the acquisition of cloud-free satellite imagery very difficult. Therefore, we focused on developing image datasets with both a high temporal resolution and medium spatial resolution by harmonizing the time-series of MOD09GA Normalized Difference Vegetation Index (NDVI) images and 30-m-resolution GF-1 WFV images using the improved Kalman filter model. The harmonized images, GF-1 images, and Landsat 8 images were then combined and used to monitor the summer corn growth from 5th June to 6th October, 2014, in three counties of Hebei Province, China, in conjunction with meteorological data and MODIS Evapotranspiration Data Set. The prediction residuals ( Δ P R K ) in NDVI between the GF-1 observations and the harmonized images was in the range of −0.2 to 0.2 with Gauss distribution. Moreover, the obtained phenological curves manifested distinctive growth features for summer corn at field scales. Changes in NDVI over time were more effectively evaluated and represented corn growth trends, when considered in conjunction with meteorological data and MODIS Evapotranspiration Data Set. We observed that the NDVI of summer corn showed a process of first decreasing and then rising in the early growing stage and discuss how the temperature and moisture of the environment changed with the growth stage. The study demonstrated that the synthesized dataset constructed using this methodology was highly accurate, with high temporal resolution and medium spatial resolution and it was possible to harmonize multi-source remote sensing imagery by the improved Kalman filter for long-term field monitoring. [ABSTRACT FROM AUTHOR]

Accurate urban land-use mapping is a challenging task in the remote-sensing field. With the availability of diverse remote sensors, synthetic use and integration of multisource data provides an opportunity for improving urban land-use classification accuracy. Neural networks for Deep Learning have achieved very promising results in computer-vision tasks, such as image classification and object detection. However, the problem of designing an effective deep-learning model for the fusion of multisource remote-sensing data still remains. To tackle this issue, this paper proposes a modified two-branch convolutional neural network for the adaptive fusion of hyperspectral imagery (HSI) and Light Detection and Ranging (LiDAR) data. Specifically, the proposed model consists of a HSI branch and a LiDAR branch, sharing the same network structure to reduce the time cost of network design. A residual block is utilized in each branch to extract hierarchical, parallel, and multiscale features. An adaptive-feature fusion module is proposed to integrate HSI and LiDAR features in a more reasonable and natural way (based on "Squeeze-and-Excitation Networks"). Experiments indicate that the proposed two-branch network shows good performance, with an overall accuracy of almost 92%. Compared with single-source data, the introduction of multisource data improves accuracy by at least 8%. The adaptive fusion model can also increase classification accuracy by more than 3% when compared with the feature-stacking method (simple concatenation). The results demonstrate that the proposed network can effectively extract and fuse features for a better urban land-use mapping accuracy. [ABSTRACT FROM AUTHOR]

The advent of the era of big remote sensing data has transformed traditional data management and analysis models, among which visualization analysis has gradually become an effective method, and map tiles for remote sensing data have always played an important role. However, in high-latitude regions, especially in polar regions, the deformation caused by map projection still exists, which lowers the accuracy of global or large-scale visual analysis, as well as the execution efficiency of big data. To solve the above problems, this paper proposes an algorithm called HexTile, which uses a hexagonal discrete global grid system (DGGS) model to effectively avoid problems caused by map projection and ensure global consistency. At the same time, the algorithm was implemented based on the Spark platform, which also has advantages in efficiency. Based on the DGGS model, hierarchical hexagon map tile construction and a visualization algorithm were designed, including hexagonal slicing, merging, and stitching. The above algorithms were parallelized in Spark to improve the big data execution efficiency. Experiments were carried out with Landsat-8, and the results show that the HexTile algorithm can not only guarantee the quality of global data, but also give full play to the advantages of the cluster in terms of efficiency. Additionally, the visualization was conducted with Cesium and OpenLayers to validate the integration and completeness of hexagon tiles. The scheme proposed in this paper could provide a reference for spatiotemporal big data visualization technology. [ABSTRACT FROM AUTHOR]

• A bibliometric and content analysis was conducted to comprehensively review and analyze deep learning research in cropland field identification. • The paper discusses the challenges of deep learning-based research on cropland field identification, providing readers with insights and directions for future research in the field • This study fills the gap by providing a systematically summarized review of this research area. The cropland field (CF) is the basic unit of agricultural production and a key element of precision agriculture. High-precision delineations of CF boundaries provide a reliable data foundation for field labor and mechanized operations. In recent years, with the dual advancements in remote sensing satellite technology and artificial intelligence, enabling the extraction of CF information on a wide scale and with high precision, research on CF identification based on deep learning (DL) has emerged as a highly esteemed direction in this field. To comprehend the developmental trends within this field, this study employs bibliometric and content analysis methods to comprehensively review and analyze DL research in the field of CF identification from various perspectives. Initially, 93 relevant literature pieces were retrieved and screened from two databases, the Web of Science Core Collection and the Chinese Science Citation Database, for review. The previous studies underwent quantitative analysis using bibliometric software across five dimensions: publication year, literature type and publication journal, country, author, and keyword. Subsequently, we analyze the current status and trends of employing DL in the field of CF identification from four perspectives: remote sensing data sources, DL models, types of CF extraction results, and sample datasets. Simultaneously, we combed through current publicly available sample datasets and data products that can be referenced to produce sample datasets for CFs. Finally, the challenges and future research focus of DL-based CF identification research are discussed. This paper provides both qualitative and quantitative analyses of research on DL-based CF identification, elucidating the current status, development trends, challenges, and future research focuses. [ABSTRACT FROM AUTHOR]

• We proposed a delineating field parcel model (TSANet) based on satellite image time series. • TSANet learn the relevance of spatial-spectral-temporal feature representation. • TSANet is robust across space and time. • TSANet performs better than pervious methods. • The time series data from the main growing period has a greater impact. Satellite image time series (SITS), such as Sentinel-2 imagery, plays a crucial role in the delineation of agricultural fields by reducing the impacts of ambiguities due to the spatial arrangement of field boundaries. Existing delineate field parcel models rely extensively on spatial features derived from single-date imagery. However, several studies have exploited the potential of SITS to effectively tackle the complexities associated with the intrinsic consistency between agricultural fields and their boundaries. This paper proposes a novel Two-Stream Attention convolutional neural network (TSANet) to capture the subtle difference between agricultural fields from SITS. Specifically, a field temporal semantic stream is introduced to adaptively leverage the significance of spatial-spectral-temporal feature representation associated with the location of agricultural parcels, especially where transitions in crop types take place. Considering the consistency between field parcels and their boundaries, we developed a field boundary prediction stream to enhance the extraction of edge features, particularly for the extraction of small and irregular agricultural parcels. Moreover, a field parcel refining block is employed to further enhance the geometric accuracy of agricultural fields. We conducted experiments on Sentinel-2 images from the Netherlands. Results showed that our approach produced a better layout of agricultural fields, with an average F1-score of 0.91 than the existing 3D-UNet, U-TEA, and BiConvLSTM. In addition, through the analysis of both quantitative and qualitative results, the stronger robustness of the model compared to other algorithms has been verified by temporal transfer and large-scale spatial prediction. We compared the difference between SITS and the corresponding composite images, which further verified the influence of temporal variation on the proposed approach. This paper provides a general guide for delineating agricultural parcels using SITS. [ABSTRACT FROM AUTHOR]

Abstract: To recreate human movements in a virtual environment in real time, we propose a new method for real-time tracking of 3D virtual full-body motion using a depth-sensing camera. The method uses natural interaction and a non-contact mode. The 3D virtual environment was constructed using a 3D graphics engine and human joint data were calculated using images acquired from a Prime Sense depth-sensing camera. Then skeletal data for the human model in a skinned mesh animation were separated by improving the mesh modules using a 3D graphics engine. Finally, motion data from the depth sensor were combined with joint data for the human model to yield full-body control of a virtual human (VH). Experimental results show that the proposed method can drive VH full-body movements in real time based on motion-sensing data. The method was applied in virtual driving training for agricultural machinery. Trainees can become familiar with the basic operations required for driving agricultural machinery using full-body motion instead of a mouse and keyboard. The training system is inexpensive and has high safety and a strong sense of immersion. [Copyright &y& Elsevier]

Abstract: Regional crop yield prediction is a significant component of national food security assessment and food policy making. The crop growth model based on field scale is limited when it is extrapolated to regional scale to estimate crop yield due to the uncertainty of the input parameters. The data assimilation method which combines crop growth model and remotely sensed data has been proven to be the most effective method in regional yield estimation. The methods based on cost function are powerless with crop dynamic growth simulation and state variable dynamic update. However, sequence assimilation method has more advantages to overcome these problems, this paper presents a method of assimilation of time series HJ-1 A/B Normalized Difference Vegetation Index (NDVI) into the coupled model (e.g. WOrld FOod STudies (WOFOST) crop growth model and A two layer Canopy Reflectance Model (ACRM) radiative transfer mode) for winter wheat yield estimates using Ensemble Kalman Filter (EnKF) at the regional scale. The WOFOST model was selected as the crop growth model and calibrated and validated by the field measured data in order to accurately simulate the state variables and the growing process of winter wheat. The theoretically optimal time series LAI profile was obtained with the EnKF algorithm to reduce the errors which existed in both time series HJ-1 CCD NDVI and WOFOST–ACRM model. Finally, the winter wheat yield at the county level was estimated based on the optimized WOFOST model running on the wheat planting pixel. The experiment illustrates that in the potential mode, the EnKF algorithm has significantly improved the regional winter wheat yield estimates ( , RMSE=775 kg/ha) over the WOFOST simulation without assimilation ( , RMSE=2168 kg/ha) at county level compared to the official statistical yield data. Meanwhile, in the water-limited mode the results showed a high correlation ( , RMSE=3005 kg/ha) with statistical data. In general, our results indicate that EnKF is a reliable optimization method for assimilating remotely sensed data into the crop growth model for predicting regional winter wheat yield. [Copyright &y& Elsevier]

Abstract: One of the main purposes of spatio-temporal modeling is to replay and reproduce states at different historical moments. The spatio-temporal data integration is the key to building the model because it exerts a direct influence on the mode and efficiency of querying data in the database. In fact, in the previous study, the author has proposed a time-based spatio-temporal data integration method and proved that the efficiency of querying historical data with the integration method is higher than that with the widely used integration method regarding time as an attribute from the theoretical level. In the study, from the application level, the author, using real cadastral parcel alternation data and the numerical fitting method, makes a contrast analysis of these two methods in the query efficiency based on two situations of historical data query respectively and real query time data, and also further verifies the conclusion from the theoretical study. [Copyright &y& Elsevier]

Agricultural drought threatens food security. Numerous remote-sensing drought indices have been developed, but their different principles, assumptions and physical quantities make it necessary to compare their suitability for drought monitoring over large areas. Here, we analyzed the performance of three typical remote sensing-based drought indices for monitoring agricultural drought in two major agricultural production regions in Shaanxi and Henan provinces, northern China (predominantly rain-fed and irrigated agriculture, respectively): vegetation health index (VHI), temperature vegetation dryness index (TVDI) and drought severity index (DSI). We compared the agreement between these indices and the standardized precipitation index (SPI), soil moisture, winter wheat yield and National Meteorological Drought Monitoring (NMDM) maps. On average, DSI outperformed the other indices, with stronger correlations with SPI and soil moisture. DSI also corresponded better with soil moisture and NMDM maps. The jointing and grain-filling stages of winter wheat are more sensitive to water stress, indicating that winter wheat required more water during these stages. Moreover, the correlations between the drought indices and SPI, soil moisture, and winter wheat yield were generally stronger in Shaanxi province than in Henan province, suggesting that remote-sensing drought indices provide more accurate predictions of the impacts of drought in predominantly rain-fed agricultural areas. [ABSTRACT FROM AUTHOR]

Coastal land cover classification is a significant yet challenging task in remote sensing because of the complex and fragmented nature of coastal landscapes. However, availability of multitemporal and multisensor remote sensing data provides opportunities to improve classification accuracy. Meanwhile, rapid development of deep learning has achieved astonishing results in computer vision tasks and has also been a popular topic in the field of remote sensing. Nevertheless, designing an effective and concise deep learning model for coastal land cover classification remains problematic. To tackle this issue, we propose a multibranch convolutional neural network (MBCNN) for the fusion of multitemporal and multisensor Sentinel data to improve coastal land cover classification accuracy. The proposed model leverages a series of deformable convolutional neural networks to extract representative features from a single-source dataset. Extracted features are aggregated through an adaptive feature fusion module to predict final land cover categories. Experimental results indicate that the proposed MBCNN shows good performance, with an overall accuracy of 93.78% and a Kappa coefficient of 0.9297. Inclusion of multitemporal data improves accuracy by an average of 6.85%, while multisensor data contributes to 3.24% of accuracy increase. Additionally, the featured fusion module in this study also increases accuracy by about 2% when compared with the feature-stacking method. Results demonstrate that the proposed method can effectively mine and fuse multitemporal and multisource Sentinel data, which improves coastal land cover classification accuracy. [ABSTRACT FROM AUTHOR]

Information on the body shape of pigs is a key indicator to monitor their performance and health and to control or predict their market weight. Manual measurements are among the most common ways to obtain an indication of animal growth. However, this approach is laborious and difficult, and it may be stressful for both the pigs and the stockman. The present paper proposes the implementation of a Structure from Motion (SfM) photogrammetry approach as a new tool for on-barn animal reconstruction applications. This is possible also to new software tools allowing automatic estimation of camera parameters during the reconstruction process even without a preliminary calibration phase. An analysis on pig body 3D SfM characterization is here proposed, carried out under different conditions in terms of number of camera poses and animal movements. The work takes advantage of the total reconstructed surface as reference index to quantify the quality of the achieved 3D reconstruction, showing how as much as 80% of the total animal area can be characterized. [ABSTRACT FROM AUTHOR]

Highlights • A fully automatic pose normalization framework is proposed. • The proposed pose normalization pipeline provide a solution for PLF. • A point clouds processing software for livestock body measurement can be downloaded. Abstract The shape of a livestock is a vital indicator of its health and value, whether for breeding or growth. Cutting-edge remote sensing technology provides an efficient and affordable way for acquiring point clouds of livestock, so that automated procedures of obtaining body measurements need to be established. A novel pose normalization method for 3D point clouds of livestock with similar forms of cows or pigs based on its bilateral symmetry properties is proposed in order to increase the degree of measuring automation. The proposed algorithm is combined in a hybrid scheme, which serves as the pose normalization procedure in an automatic body measurement system for livestock. Our extensive experiments on both synthetic and real world point clouds data show that the proposed approach has potential for generalizing well across livestock species and handles noise successfully in test data. In addition, the proposed pose normalization scheme outperforms current standard approach Principal Component Analysis (PCA) and state-of-the-art pose normalization method for pigs. [ABSTRACT FROM AUTHOR]

Highlights • We proposed an up-scaling method of assimilating reflectance into model. • Constraint of key input parameters for PROSAIL through WOFOST output. • A faster data-assimilation strategy for 30-m resolution was developed. • Assimilating up-scaling reflectance achieved the highest yield estimation. Abstract To estimate regional-scale winter wheat (Triticum aestivum) yield, we developed a data-assimilation scheme that assimilates remotely sensed reflectance into a coupled crop growth–radiative transfer model. We generated a time series of 8-day, 30-m-resolution synthetic Kalman Smoothed reflectance by combining MODIS surface reflectance products with Landsat surface reflectance using a KS algorithm. We evaluated the assimilation performance using datasets with different spatial and temporal scales (e.g., three dates for the 30-m Landsat reflectance, 8-day and 1-km MODIS surface reflectance, and 8-day and 30-m synthetic KS reflectance) into the coupled WOFOST–PROSAIL model. Then we constructed a four-dimensional variational data assimilation (4DVar) cost function to account for differences between the observed and simulated reflectance. We used the shuffled complex evolution–University of Arizona (SCE-UA) algorithm to minimize the 4DVar cost function and optimize important input parameters of the coupled model. The optimized parameters were used to drive WOFOST and estimate county-level winter wheat yield in a region of China. By assimilating the synthetic KS reflectance data, we achieved the most accurate yield estimates (R 2 = 0.44, 0.39, and 0.30; RMSE = 598, 1288, and 595 kg/ha for 2009, 2013, and 2014, respectively), followed by Landsat reflectance (R 2 = 0.21, 0.22, and 0.33; RMSE = 915, 1422, and 637 kg/ha for 2009, 2013, and 2014, respectively) and MODIS reflectance (R 2 = 0.49, 0.05, and 0.22; RMSE = 1136, 1468, and 700 kg/ha for 2009, 2013, and 2014, respectively) at the county level. Thus, our method improves the reliability of regional-scale crop yield estimates. [ABSTRACT FROM AUTHOR]

Body measurement plays an important role in animal breeding and production. In this paper, we develop a novel portable and automatic measurement system for pig body size. Firstly, we utilize two depth cameras to capture the point clouds of the scene with a pig from two viewpoints and implement the registration of the obtained point clouds. Secondly, we resort to Random Sample Consensus (RANSAC) to remove the background point cloud and extract the foreground pig point cloud with a Euclidean clustering. Finally, body measurement is conducted via pose normalization and morphological constraints on pig cloud. We evaluate the proposed system on 20 sets of the scenes with a pig in a commercial pig farm. Experimental results show that the pig object extraction algorithm achieves good performance. The average relative errors for body width, hip width, and body height are 10.30%, 5.87% and 7.01% respectively, which demonstrates the efficacy of the proposed system. [ABSTRACT FROM AUTHOR]

Spatial data partitioning (SDP) plays a powerful role in distributed storage and parallel computing for spatial data. However, due to skew distribution of spatial data and varying volume of spatial vector objects, it leads to a significant challenge to ensure both optimal performance of spatial operation and data balance in the cluster. To tackle this problem, we proposed a spatial coding-based approach for partitioning big spatial data in Hadoop. This approach, firstly, compressed the whole big spatial data based on spatial coding matrix to create a sensing information set (SIS), including spatial code, size, count and other information. SIS was then employed to build spatial partitioning matrix, which was used to spilt all spatial objects into different partitions in the cluster finally. Based on our approach, the neighbouring spatial objects can be partitioned into the same block. At the same time, it also can minimize the data skew in Hadoop distributed file system (HDFS). The presented approach with a case study in this paper is compared against random sampling based partitioning, with three measurement standards, namely, the spatial index quality, data skew in HDFS, and range query performance. The experimental results show that our method based on spatial coding technique can improve the query performance of big spatial data, as well as the data balance in HDFS. We implemented and deployed this approach in Hadoop, and it is also able to support efficiently any other distributed big spatial data systems. [ABSTRACT FROM AUTHOR]

As increasing number of studies for shape measurement purposes in livestock farming by using consumer depth cameras, many software have been developed in order to measure livestock conformation. However, many of these softwares were designed only for specific livestock or body part of specific livestock with very limited body measurements. To be more flexible and general compared to the current software provided in the literature, an interactive software LSSA_CAU is developed to estimate body measurements of livestock based on 3d point clouds data. Livestock with similar forms of cows or pigs and standing with her head forward is assumed for designing algorithm used in LSSA_CAU. This software provides a set of tools for loading, rendering, segmenting, pose normalizing, measuring point clouds data of whole body surface of livestock in a semiautomatic manner. In order to validate the software, both synthetic and real world point clouds data of livestock were processed by using the LSSA_CAU. Our experiments show that the proposed software generalizes well across livestock species and supports customized body measurements. An updated LSSA_CAU version can be downloaded freely from https://github.com/LiveStockShapeAnalysis to livestock industry and research. [ABSTRACT FROM AUTHOR]

Increasing drought poses a big threat to food security over recent decades, highlighting the need for effective tools and adequate information for drought monitoring and mitigation. This study analyzed the performance of five climate-based drought indices and soil moisture measurements for monitoring winter wheat drought threat in China. We employed the Standardized Precipitation Index (SPI), the Standardized Precipitation Evapotranspiration Index (SPEI), the Palmer Drought Severity Index (PDSI), the Palmer Z index and the self-calibrated Palmer Drought Severity Index (scPDSI). On average, soil moisture at 50-cm depth correlated better with winter wheat yield during October-December of the previous year of harvest compared to soil moisture at 10-cm and 20-cm depths. Moreover, the 3-layer soil moisture and reference evapotranspiration (ETo) correlated weakly (Pearson’s r < 0.3) and even negatively with winter wheat yield. The SPI and SPEI at shorter (1–5 months) timescales during September-December in the previous year of harvest showed higher correlations with winter wheat yield. The SPEI trend in March-June has a significant positive influence on trend in winter wheat yield ( r > 0.40, p < 0.05). The climate-based drought indices can facilitate crop drought monitoring in water-limited regions due to the wide-availability of climatic data, particularly in the light of uncertainties arising from the crop model. Among the investigated indices, results revealed that the SPEI is advantageous for drought monitoring over the study area due to its multiscalarity and effective characterization of agricultural droughts. [ABSTRACT FROM AUTHOR]

The effects of varieties, producing areas, ears, and ear positions of maize on near-infrared (NIR) spectra were investigated to determine the factors causing the differences in NIR fingerprints of maize varieties. A total of 130 inbred lines were grown in two regions in China, and 12,350 kernel samples were analyzed through NIR spectroscopy. Spectral differences among varieties, producing areas, ears, and ear positions were determined and compared on the basis of pretreated spectra. The bands at 1300–1470, 1768–1949, 2010–2064, and 2235–2311 nm were mainly affected by the producing area. Band selection and principal component analysis were applied to improve the influence of variety on NIR spectra by processing the pretreated spectra. The degrees of the influence of varieties, producing areas, ears, and ear positions were calculated, and the percentages of the influence of varieties, producing areas, ears, and ear positions were 45.40%, 42.66%, 8.22%, and 3.72%, respectively. Therefore, genetic differences among maize inbred lines are the main factors accounted for NIR spectral differences. Producing area is a secondary factor. These results could provide a reference for researchers who authenticate varieties, perform geographical origin traceabilities, and conduct maize seed breeding. [ABSTRACT FROM AUTHOR]

The current detection methods for maize seed damage and viability assessment are usually time-consuming, tedious, and costly. In this investigation, near infrared spectroscopy (NIRS), a nondestructive and rapid analytical method, was explored to analyze frost-damaged and non-viable seeds. Principal component analysis (PCA), partial least squares (PLS) and orthogonal linear discriminant analysis (OLDA) were combined to extract feature from near infrared (NIR) spectra. PLS + OLDA can extract difference characteristics of normal and frost-damaged seeds more efficiently than PCA + OLDA. Three classification algorithms were utilized and compared: Support vector machine (SVM), biomimetic pattern recognition (BPR), and mahalanobis distance (MD). BPR can classify normal and frost-damaged seeds better and achieved the highest average accuracy of 97%. Discrimination model of viable and non-viable seeds in frost-damaged seeds based on SVM, BPR and MD were built and achieved accuracies of 94%, 97.25% and 89.5% respectively. BPR model yielded the most correct value in predicting germination rate of validation set, and improved the germination rate of validation set dramatically from 27.5% to 100% by screening out non-viable seeds. NIRS and chemometrics as demonstrated in this paper can provide a novel method which can assess and improve quality of maize seed quickly and inexpensively. [ABSTRACT FROM AUTHOR]

Crop residues are effective for the prevention of soil erosion. The crop residue cover (CRC) can be mapped by remote sensing. Different morphologies of crop residue will affect the spectral reflectance, reducing the accuracy of CRC estimation by multispectral data. However, the influence of residue morphology is not fully considered on the accuracy of CRC mapping using satellite images. In addition, the spectral indices are easily saturated and less sensitive to high-density areas of crop residue. This study selected four maize planting sites to obtain hyperspectral reflectance and unmanned aerial vehicle (UAV) images. The effects of CRC and residue morphology on spectral reflectance were analyzed, and a new Residue Adjust Normalized Difference Residue Index (RANDRI) was proposed. UAV images were used to extract ground CRC data for training a CRC prediction model based on Sentinel-2 MSI data. Finally, the piecewise prediction model based on different residue indices was used to map CRC. The study results highlighted a linear relationship between the reflectance intersection of shortwave infrared 2 reflectance and red edge 3 of Sentinel-2 MSI with different residual morphologies, called the residue line. The model accuracy of RANDRI optimized by residual line parameters was better than that of the Normalized Difference Residue Index and Soil Adjust Normalized Difference Residue Index (SANDRI) in the high-density area of crop residue. RANDRI can weaken the influence of residue morphologies on modeling accuracy. The CRC spatial distribution by the piecewise SANDRI+RANDRI model was more consistent with CRC measured than that of the RANDRI models individually. The determination coefficient of the piecewise model was 0.82, and the relative error was 10.66%. The piecewise model can effectively improve the anti-saturation ability of the spectral indices. We suggest a rapid and accurate approach for monitoring the CRC and provide a more suitable CRC mapping strategy for high-density areas of crop residue using multispectral remote sensing data. • Crop residue cover was mapped using remote sensing. • The effects of crop residue cover and residue morphology on spectral reflectance were analyzed. • Novel crop residue cover prediction models were suggested and analyzed. [ABSTRACT FROM AUTHOR]

Recent advances in laser scanning hardware have allowed rapid generation of high-resolution digital terrain models (DTMs) for large areas. However, the automatic discrimination of ground and non-ground light detection and ranging (lidar) points in areas covered by densely packed buildings or dense vegetation is difficult. In this paper, we introduce a new hierarchical moving curve-fitting filter algorithm that is designed to automatically and rapidly filter lidar data to permit automatic DTM generation. This algorithm is based on fitting a second-degree polynomial surface using flexible tiles of moving blocks and an adaptive threshold. The initial tile size is determined by the size of the largest building in the study area. Based on an adaptive threshold, non-ground points and ground points are classified and labelled step by step. In addition, we used a multi-scale weighted interpolation method to estimate the bare-earth elevation for non-ground points and obtain a recovered terrain model. Our experiments in four study areas showed that the new filtering method can separate ground and non-ground points in both urban areas and those covered by dense vegetation. The filter error ranged from 4.08% to 9.40% for Type I errors, from 2.48% to 7.63% for Type II errors, and from 5.01% to 7.40% for total errors. These errors are lower than those of triangulated irregular network filter algorithms. [ABSTRACT FROM PUBLISHER]

To predict regional-scale winter wheat yield, we developed a crop model and data assimilation framework that assimilated leaf area index (LAI) derived from Landsat TM and MODIS data into the WOFOST crop growth model. We measured LAI during seven phenological phases in two agricultural cities in China’s Hebei Province. To reduce cloud contamination, we applied Savitzky–Golay (S–G) filtering to the MODIS LAI products to obtain a filtered LAI. We then regressed field-measured LAI on Landsat TM vegetation indices to derive multi-temporal TM LAIs. We developed a nonlinear method to adjust LAI by accounting for the scale mismatch between the remotely sensed data and the model’s state variables. The TM LAI and scale-adjusted LAI datasets were assimilated into the WOFOST model to allow evaluation of the yield estimation accuracy. We constructed a four-dimensional variational data assimilation (4DVar) cost function to account for the observations and model errors during key phenological stages. We used the shuffled complex evolution–University of Arizona algorithm to minimize the 4DVar cost function between the remotely sensed and modeled LAI and to optimize two important WOFOST parameters. Finally, we simulated winter wheat yield in a 1-km grid for cells with at least 50% of their area occupied by winter wheat using the optimized WOFOST, and aggregated the results at a regional scale. The scale adjustment substantially improved the accuracy of regional wheat yield predictions ( R 2 = 0.48; RMSE = 151.92 kg ha −1 ) compared with the unassimilated results ( R 2 = 0.23; RMSE = 373.6 kg ha −1 ) and the TM LAI results ( R 2 = 0.27; RMSE = 191.6 kg ha −1 ). Thus, the assimilation performance depends strongly on the LAI retrieval accuracy and the scaling correction. Our research provides a scheme to employ remotely sensed data, ground-measured data, and a crop growth model to improve regional crop yield estimates. [ABSTRACT FROM AUTHOR]

Near infrared spectroscopy (NIRS) has been used to identify variety authenticity of bare maize kernels. However, maize seeds are coated with seed coating agents in practice. Therefore it is of great significance to investigate the feasibility of identifying coated maize kernels by NIRS. This study employed NIRS to quickly determine the variety to which a sample of coated seed belonged. The NIR spectra of clean and coated seeds were obtained using MPA spectrometry in diffuse reflectance mode by three methods. Influence of seed coating agent on NIR spectra was discussed based on spectra collected from whole single seed by method 1. In method 2, to eliminate the influence of seed coat, the seed coat agent on the back side of the seed was polished away. In method 3, clean and coated seeds were cut open along the crease on the embryo side, and the sections were scanned by the spectrometer, so as to acquire information on the seed, and to avoid the influence of the seed coating agent. Then, support vector machine (SVM), soft independent modeling of class analogy (SIMCA), and biomimetic pattern recognition (BPR) were employed to establish the identification model for four maize varieties. Performance of variety models based on spectra measured by method 1 and 2 were poor. In method 3, the SIMCA model showed better performance than SVM and BPR models, and achieved an accuracy rate of 97.5%. The results demonstrated the feasibility of utilizing NIRS and chemometrics, as an objective and rapid method for the identification of maize seeds with seed coating agents. [ABSTRACT FROM AUTHOR]

The enhancement of cultivated land quality is an important measure to improve the production capability and ensure the food safety. At the construction course of cultivated land quality informatization, novel methods and techniques are promising to improve the current working pattern as well as raise the efficiency of cultivated land quality management. Irrigation guarantee capability is an important element of cultivated land quality monitoring, evaluation and construction. Evapotranspiration (ET) derived from remote sensing can be used for rapid monitoring of irrigation guarantee capability of cultivated land at the regional scale. In order to improve the acquisition efficiency of the regional cultivated land quality monitoring, a new evaluation method was proposed for irrigation capability evaluation of cultivated land based on Moderate Resolution Imaging Spectroradiometer (MODIS) ET products. First, in order to reduce the representative errors of meteorological data, the relationship between the monthly potential evapotranspiration (PET) parameter derived from MODIS evaporation products and the reference crop evapotranspiration (ET0) calculated from observed meteorological data with the Penman-Monteith (P-M) formula was analyzed. The continuous ET0 in space was obtained from the regression model. And then, water requirements for crop were obtained by the map of crop type from the classification of Landsat TM data and space-continuous ET0. Furthermore, the annual water requirement was calculated according to the difference of the water requirement for crop and the rainfall which was effectively consumed by crop. Additionally, based on the regional water balance principle, the actual quantity of irrigation was obtained from the difference of actual evaporation derived from ET products of MODIS and effective rainfall. The evaluation index of irrigation guarantee capability is defined as the ratio of the annual irrigation requirement and the actual quantity of irrigation, and used for the monitoring and evaluation of cultivated land irrigation guarantee capability. Finally, application and analysis were conducted in Hengshui City, Hebei Province, China. The R2 of the regression model between the PET and ET0 from meteorological stations reached 0.89. And the calculated results of the evaluation index of irrigation guarantee capability from 2005 to 2012 accurately reflected temporal-spatial variations for the cultivated land irrigation capability. Meanwhile, the comprehensive evaluation of irrigation capability, which was from the supervised classification results based on actual survey, had a good agreement with the classification results of irrigation probability in the gradation on agriculture land quality which had been updated in 2012. The area with no grade difference was up to 37% of the total cells, 38% of the study area had one-grade difference, and the area with two-grade difference was 19% of the study area. The area with three-grade difference only accounted for 6%. The grade difference of more than 75% of the cultivated land was less than one grade. Errors were mainly concentrated in the cultivated land around the city, because the MOD16A2 product with 1-km resolution was inadequate to accurately represent the information of that complex planting structure of cultivated land, and this problem would be solved with the development and improvement of remote sensing earth observation systems with higher resolution. The evaluation index of irrigation capability proposed in this paper has the advantage of clear physical meaning and easy data accessing. The experiment results indicate that the method can meet the needs of the regional cultivated land quality monitoring and evaluation. [ABSTRACT FROM AUTHOR]

The results of cultivated land quality gradation are made of the results of county, provincial, national levels. The results at the provincial level are integrated by the results at the county level. Provincial integration is an essential link in cultivated land quality grading work. The traditional provincial integration methods excessively depend on the provincial integration base map, which makes the integration efficiency low. Moreover, the quality of integration work completely depends on the quality of integration base map. Based on these defects, this paper comes up with a method that uses the grid instead of the integration base map. In provincial integration work, we need to build traceability relation between county units and provincial units. It requires all county units can find provincial units and all provincial units have their corresponding county units. Moreover, there is a principle we have to abide by: the ownership, the land type and the grade should be coincident between the county units and corresponding provincial units. That is "ownership-land type-grade" coincident principle. The purpose of this method is to make spatial distribution of provincial cultivated land quality is similar to that of the county when abiding by this principle. First we need to classify the county results according to "ownership-land type-grade". Then we determine the corresponding grid category according to the area dominant principle. Through the spatial nearest neighboring method, we find the grid unit closest to the unit at the county level to build "Grid-County grading unit" relations. But maybe there are some categories which can't be found in the provincial grids. Based this situation, the barycenter of the missing category was firstly calculated, then an uncultivated area grid closest to the barycenter was searched out, and lastly this grid was marked as the missing category. The grid coding method proposed in this paper stipulates that grid code is formed by county's administrative code, the grid rank, quality gradation and land class code. The length of the code is 21. At last, this paper uses the mean center and standard deviational ellipse to test the similarity of the spatial distribution of cultivated land before and after integration. This paper takes Daxing district, Bejing as a study area. By "ownership-land type-grade", there are 8 categories in Daxing. According to the distribution of cultivated land in Daxing district, 688 valid cultivated land grids were finally determined. Using the method in this article, we completed the integration at the provincial level for Daxing. After test, it showed that the difference of mean center between provincial grid results and county results is only 405.6 m, and the difference of distribution direction is only 0.34°, which means that this method can ensure the consistency of spatial distribution of cultivated land at different levels. Compared with the method which depends on the integration base map, the method based on grid doesn't make base map, reduces workload and improves work efficiency. This method orientates the provincial cultivated land into each grid and codes for these grids. Through grid code, we can quickly search cultivated land quality in the corresponding position, which is very convenient for both management and application. [ABSTRACT FROM AUTHOR]

Evaluation of arable land ecosystem services capacity and arable land-use intensity (ALUI) is important for recognising key regional factors that impact arable land attributes changes, which is crucial for planning sustainable patterns of arable land use. The chronic lack of coordination between these two types of evaluation studies has made it hard to provide enough information for developing arable land-use management and control policies. Here, we generated a 1-km-grid map of arable land potential yield and county-level arable land productive-capacity. The impact of land-use and land-cover change on county-level total arable land productive-capacity during 1990–2010 had been estimated. Then we determined the aggregation–distribution characteristics of four indexes (i.e. average arable land potential yield, average ALUI, total arable land area and arable land productive-capacity reserves) at the county-level by the k-means algorithm to assess the regional coordination between arable land productive-capacity protection and arable land use. The results show that during 1990–2010, land-use change led to arable land productive-capacity decreases in 2007 of China's 2733 counties (nearly 73.5% of the total counties' count). Most of these counties are in central and southern China, and their corresponding arable land productive-capacity decrement rates are generally < 6.15%. Counties with decrement rates > 6.15% are mainly in the Yangtze and Pearl River delta regions. The geographical detector shows that county-level arable land-area change is a primary factor that drives county-level arable land productive-capacity increase. Its determinant power can be quantified as 74.154%. In contrast, its determinant power to county-level arable land productive-capacity decrease is only 38.542%, which demonstrates that occupy high-capacity arable land and supplement low-capacity arable land have a greater role in causing reduction of county arable land productive-capacity. Total arable land productive-capacity and use intensity show only slight determinant power to county-level arable land productive-capacity decrease. It indicates that insufficient attention has been paid to the protection of arable land productive-capacity and the farmers' willingness in the implementation of China requisition-compensation balance policy. The aggregation–distribution characteristics show that arable land productive-capacity protection is in coordination with arable land use for most of the provinces in China. Arable land with high or medium potential yield tends to be used at high or medium intensity. A lack of coordination is most evident in the insufficient ALUI, particularly in seven of the thirteen major grain-producing provinces. Other evidence of weak coordination is in the low potential yield versus high farming conditions and willingness, where unsuited planting modes should be prevented. Lastly, challenges for exploring sustainable arable land use path have been discussed. This study is greatly instructive for recognising interrelations between natural conditions and arable land-use patterns and for exploring shortcomings that impede regionally sustainable arable land use. • Impact of LUCC on county-level arable land productivity during 1990–2010 is estimated. • Difference in determinant power to arable land productivity decrease and increase is detected. • Regional coordination between arable land productivity and use intensity is assessed. • Correlation between arable land potential yield and its distance to urban is assessed. • Generate county-level normalised total arable land productive capacity dataset. [ABSTRACT FROM AUTHOR]

Since the numbers and capacities of dairy cattle farms are increasing with every passing day, computer aided studies for the management of these farms become more important and are widely used in daily life. In this study, we assessed the potential of Xtion as a point cloud data acquisition system for the body measurements of Holstein cows in the context of dairy cow conformation. For this purpose, we selected Xtion for point cloud data acquisition and chose a dairy cow model and a dairy cow as the experimental subjects. In an indoor environment, three dimensional laser scanners with high precision were employed to get point cloud data of the cow model as comparison data, and Xtion was used for acquiring point cloud data at different distances away from the cow model as test data. After aligning the comparison data and test data by using commercial point cloud processing software, statistical errors between comparison data and test data including positive maximum distance, negative maximum distance, positive average distance, negative average distance, standard deviation, and RMS error were calculated by the professional point cloud software in order to quantitatively analyze the precision and density of point cloud data from Xtion at different distances. The test results indicate that the errors almost increased linearly with increasing of the distance between Xtion and subject. The average errors were less than ±5mm on the condition that the distance from Xtion to the subject were between 0.6m and 1.2m. The average errors were less than ±10mm on the condition that the distance between Xtion and the subject were between 1.2m and 1.8m. Maximum errors were always less than ±20mm. The density of point clouds decreased exponentially with increasing of the distance from Xtion to the subject to such an extent that body measurements were impossible to get on account of missing the mark points on the body. These results imply that the appropriate distance between Xtion and a cow is between 0.6m and 1.2m. Under the dairy cow breeding environment, body measurements including chest width, thurl width, rear leg side view, front nipple length, rear udder width, and rear udder height of cows were first determined manually, by direct measurement. Then we used Xtion to acquire point cloud data at a distance of less than 1.2 meters from the cow. Visualization of the point cloud data and interactive measurement of the cow body based on point cloud data from Xtion were performed by Meshlab so as to qualitatively analyze the sunlight and surface materials’ influence on the quality of point cloud data acquired from Xtion under dairy farm conditions. The results indicate that Xtion failed to give normal operation under the sunlight due to the presence of the IR rays in the sunlight. Point cloud acquisition from Xtion may have some small holes due to the material and appearance of a live cow body. The relative errors of comparing the body measurements obtained by Meshlab with the manual measurements were less than 10%, which indicates that Xtion is appropriate for body measurements of Holstein cows. [ABSTRACT FROM AUTHOR]

Abstract: In object-oriented classification approaches, small sample size and high dimensionality of features are the two main characteristics. In order to effectively use the rich features of the image objects, in this study, the Relief algorithms were improved in terms of aspects of randomly drawing samples, the influence of sample quantity variance, and iteration times to evaluate the features. Through experiments in WorldView-2 images, the two classification results were contrasted between 36 dimension feature sets selected from Initials and initial 111 dimension feature sets. The results showed that the dimension disaster was avoided efficiently, while the precision and speed of classification were improved as well. Respectively, the overall accuracy and kappa coefficient using the optimized feature sets with the improved Relief algorithm were increased by 6% and 11% compared with using all feature sets. Therefore, the feature space of object-oriented classification is effectively optimized with the proposed methods. [Copyright &y& Elsevier]

Agricultural greenhouse (AG), one of the fastest-growing technology-based approaches worldwide in terms of controlling the environmental conditions of crops, plays an essential role in food production, resource conservation and the rural economy, but has also caused environmental and socio-economic problems due to policy promotion and market demand. Therefore, long-term monitoring of AG is of utmost importance for the sustainable management of protected agriculture, and previous efforts have verified the effectiveness of remote sensing-based techniques for mono-temporal AG mapping in a relatively small area. However, currently, a continuous annual AG remote sensing-based dataset at large-scale is generally unavailable. In this study, an annual AG mapping method oriented to the provincial area and long-term period was developed to produce the first Landsat-derived annual AG dataset in Shandong province, China from 1989 to 2018 on the Google Earth Engine (GEE) platform. The mapping window for each year was selected based on the vegetation growth and the phenological information, which was critical in distinguishing AG from other misclassified categories. Classification for each year was carried out initially based on the random forest classifier after the feature optimization. A temporal consistency correction algorithm based on classification probability was then proposed to the classified AG maps for further improvement. Finally, the average User's Accuracy, Producer's Accuracy and F1-score of AG based on visually-interpreted samples over 30 years reached 96.56%, 86.64% and 0.911, respectively. Furthermore, we also found that the ranked features via calculating the importance of each tested feature resulted in the highest accuracy and the strongest stability in the initial classification stage, and the proposed temporal consistency correction algorithm improved the final products by approximately five percent on average. In general, the resultant AG sequence dataset from our study has revealed the expansion of this typical object of "Human–Nature" interaction in agriculture and has a potential application in use of greenhouse-related technology and the scientific planning of protected agriculture. [ABSTRACT FROM AUTHOR]

A Semivariogram, as defined in geostatistics, is a powerful tool for texture extraction of remotely sensed images. However, the traditional texture features extracted by a semivariogram are generally for pixel-based classification. Moreover, most studies have been based on the original computation mode of semivariogram and discrete semivariance values. This article describes a set of semivariogram texture features (STFs) based on the mean square root pair difference (SRPD) to improve the accuracy of object-oriented classification (OOC) in QuickBird images. The adaptive parameters for the calculation of a semivariogram were first derived from semivariance analysis, including directions, moving window size, and lag distance. Then, 22 STFs were extracted from the discrete and mean/standard deviation semivariance, and 15 features were selected from the extracted STFs based on feature optimization. Then five grey-level co-occurrence matrix (GLCM) texture features (mean, homogeneity, contrast, angular second moment, and entropy) were calculated based on segmented image objects using the panchromatic band. A comparison of classification results demonstrates that the STFs described in this article are useful supplement information for the spectral OOC, and the spectral + STFs classification method can be used to obtain a higher classification accuracy than can the combination of spectral and GLCM features. [ABSTRACT FROM AUTHOR]

Lodging is one of the major problems in maize production which causes severe yield loss every year all over the world. In the present study, the lodging suitability of different maize varieties in target growing environments was investigated based on geographical information science. A total of 401 maize planting counties in northeast China and northern China were selected as study areas. The mean and standard deviation of environment accumulated temperature in vegetative stage of maize were calculated from raw temperature data obtained from 167 meteorology stations in these areas. The variety lodging resistance was determined based on the data of national regional variety trials for maize, and the environment lodging stress was measured using field survey data on lodging. Probability analysis based on the calculated values of environment accumulated temperature in vegetative stage of maize was utilized to determine whether a maize variety can be physically mature in a planting county, and lodging suitability of the variety was evaluated with geographical information science combining variety lodging resistance and local environment lodging stress together. A new maize variety NH1101 was taken as an example to illustrate the modeling and calculating procedures. The result shows that, from southwest to northeast of the study areas, the overall suitability trend changes from nonsuitable to suitable, then to not very suitable. And it is demonstrated that the lodging suitability is not only related to the variety resistance but also to the local environment stress. [ABSTRACT FROM AUTHOR]

Abstract: Firstly, this paper analyzes the basic principles and processes of the spatial pattern changes of land use in towns and villages, and the result shows that the land resource demands of urban development and population growth lead to the spatial pattern changes. Secondly, in order to grip land use changes better, the paper proposes a method for the simulation of spatial patterns. The simulating method can be divided into two parts: one is a quantitative forecast by using the Markov model, and the other is simulating the spatial pattern changes by using the CA model. The above two models construct the simulative model of the spatial pattern of land use in towns and villages. Finally, selecting Fangshan which is a district of Beijing as the experimental area, both the quantity and spatial pattern changing characteristics are investigated through building a changing dataset of land use by using spatial analysis methods based on the land use data in 2001, 2006 and 2008; CA–Markov is used to simulate the spatial pattern of land use in Fangshan for 2015. [Copyright &y& Elsevier]

Abstract: Lodging in maize, which is the result of the genotype-by-environment interactions, causes severe yield losses annually. There are many studies on lodging resistance of maize varieties now, but information about maize planting environment lodging stress is very rare. The environment lodging stress, which is a result of various factors, is characterized by uncertainty. Fuzzy sets theory and fuzzy logic are advantageous for dealing with the questions with uncertainties. The objective of this study is to assess the environment lodging stress for maize planting. Based on the daily weather data in the recent 59 years (1951–2009) and soil data, five counties (or cities) in ShanDong Province and HeNan Province in Huang-Huai-Hai-Plain, China, are selected as study sites; the maximum wind speed, rainfall, and potassium content in soil are chosen as stress indicators, and the overall stress level of each study site is obtained by a fuzzy synthetic evaluation approach. The consistency is shown between our calculation results and the results obtained with actual survey data on lodging in maize, indicating that the employed model is a promising approach for assessing environment lodging stress, and providing a scientific basis for maize variety extension and recommendation and comprehensive management to reduce maize planting risk and loss. [Copyright &y& Elsevier]

Abstract: Previous analyses on variety yield have usually focused on regression coefficients as an indicator to measure the stability and adaptation of a specific variety under experimental conditions. Due to the huge differences between experimental plots and farm fields, the model results from experimental plots can hardly be applied to farm fields. In this study, a regression analysis was conducted between the variety yield and an on-trial environment index (the mean yield of all varieties in the same test site). Then, using the average proportional coefficient between the on-trial environment index and the on-farm environment index (the statistical maize production yield of the growing county containing the test site) as a bridge, the on-farm environment index was converted to the corresponding on-trial environment index, which was then applied to the regression model generated from the on-trial plot-scale data. This procedure ensured the homogeneity of the model parameters and successfully predicted the yield of maize varieties under a target environment. The procedure also produced the 95% confidence interval predicted yield, making the results more practically significant. By introducing the proportional coefficient and confidence interval, the new approach provides a feasible solution for studying the performance of varieties under on-farm conditions. Finally, we used the maize variety NH1101 as an example to illustrate the modeling procedures. The results indicated that the model produced promising results. The new method provides direct support for variety recommendation, and facilitates the identification of better-adapted varieties. [Copyright &y& Elsevier]

Abstract: In this paper, the theory of artificial neural network with back-propagation algorithm (BPN) is presented, and the BPN model is used to predict the accumulated temperature for Northeast China, North China, and the Huang-Huai-Hai Plain. A total of 235 records collected from 235 meteorology stations were fed into the BPN model for training and testing. The latitude, longitude and elevation of each station were used as input variables of BPN, and the accumulated temperature as output variable. Other key network parameters, such as learning rate, momentum, the number of hidden nodes, and the learning iterations, were optimized using a trial and error approach. The optimized BPN model was compared with the multiple linear regression (MLR) model. In summary, BPN model was generally more accurate than MLR model. This infers that artificial neural network models are more applicable than regression models when predicting accumulated temperature. [Copyright &y& Elsevier]

Along with the development of the starch and grain-alcohol industries, biomass energy production has recently become important. Cassava is an important biomass energy plant. In this paper, geographic information system (GIS) and remote sensing (RS) are used, along with a knowledge of the growing environment needed for cassava and the farmland and ecology protection policy of China, to evaluate the cassava growing potential of Wuming County. The processing of spatial data is done first. Then, the evaluation principles are defined according to the spatial data and the required growth conditions. The evaluation data are obtained by spatial data analysis according with the evaluation principles. Lastly, the cassava planting potential results are verified by referencing these to cassava planting statistical data for 2005 provided by Nanning City Government of Guangxi province. This paper provides the science basis for Wuming County to develop local grain-alcohol and biomass energy industries. [ABSTRACT FROM AUTHOR]

Black soil is fertile, abundant with organic matter (OM) and is exceptional for farming. The black soil zone in northeast China is the third-largest black soil zone globally and produces a quarter of China's commodity grain. However, the soil organic matter (SOM) in this zone is declining, and the quality of cultivated land is falling off rapidly due to overexploitation and unsustainable management practices. To help develop an integrated protection strategy for black soil, this study aimed to identify the primary factors contributing to SOM degradation. The geographic detector, which can detect both linear and nonlinear relationships and the interactions based on spatial heterogeneous patterns, was used to quantitatively analyze the natural and anthropogenic factors affecting SOM concentration in northeast China. In descending order, the nine factors affecting SOM are temperature, gross domestic product (GDP), elevation, population, soil type, precipitation, soil erosion, land use, and geomorphology. The influence of all factors is significant, and the interaction of any two factors enhances their impact. The SOM concentration decreases with increased temperature, population, soil erosion, elevation and terrain undulation. SOM rises with increased precipitation, initially decreases with increasing GDP but then increases, and varies by soil type and land use. Conclusions about detailed impacts are presented in this paper. For example, wind erosion has a more significant effect than water erosion, and irrigated land has a lower SOM content than dry land. Based on the study results, protection measures, including conservation tillage, farmland shelterbelts, cross-slope ridges, terraces, and rainfed farming are recommended. The conversion of high-quality farmland to non-farm uses should be prohibited. [ABSTRACT FROM AUTHOR]

Sentinel-2 images have been widely used in studying land surface phenomena and processes, but they inevitably suffer from cloud contamination. To solve this critical optical data availability issue, it is ideal to fuse Sentinel-1 and Sentinel-2 images to create fused, cloud-free Sentinel-2-like images for facilitating land surface applications. In this paper, we propose a new data fusion model, the Multi-channels Conditional Generative Adversarial Network (MCcGAN), based on the conditional generative adversarial network, which is able to convert images from Domain A to Domain B. With the model, we were able to generate fused, cloud-free Sentinel-2-like images for a target date by using a pair of reference Sentinel-1/Sentinel-2 images and target-date Sentinel-1 images as inputs. In order to demonstrate the superiority of our method, we also compared it with other state-of-the-art methods using the same data. To make the evaluation more objective and reliable, we calculated the root-mean-square-error (RSME), R 2 , Kling–Gupta efficiency (KGE), structural similarity index (SSIM), spectral angle mapper (SAM), and peak signal-to-noise ratio (PSNR) of the simulated Sentinel-2 images generated by different methods. The results show that the simulated Sentinel-2 images generated by the MCcGAN have a higher quality and accuracy than those produced via the previous methods. [ABSTRACT FROM AUTHOR]

Recently, increasing amounts of multi-source geospatial data (raster data of satellites and textual data of meteorological stations) have been generated, which can play a cooperative and important role in many research works. Efficiently storing, organizing and managing these data is essential for their subsequent application. HBase, as a distributed storage database, is increasingly popular for the storage of unstructured data. The design of the row key of HBase is crucial to improving its efficiency, but large numbers of researchers in the geospatial area do not conduct much research on this topic. According the HBase Official Reference Guide, row keys should be kept as short as is reasonable while remaining useful for the required data access. In this paper, we propose a new row key encoding method instead of conventional stereotypes. We adopted an existing hierarchical spatio-temporal grid framework as the row key of the HBase to manage these geospatial data, with the difference that we utilized the obscure but short American Standard Code for Information Interchange (ASCII) to achieve the structure of the grid rather than the original grid code, which can be easily understood by humans but is very long. In order to demonstrate the advantage of the proposed method, we stored the daily meteorological data of 831 meteorological stations in China from 1985 to 2019 in HBase; the experimental result showed that the proposed method can not only maintain an equivalent query speed but can shorten the row key and save storage resources by 20.69% compared with the original grid codes. Meanwhile, we also utilized GF-1 imagery to test whether these improved row keys could support the storage and querying of raster data. We downloaded and stored a part of the GF-1 imagery in Henan province, China from 2017 to 2018; the total data volume reached about 500 GB. Then, we succeeded in calculating the daily normalized difference vegetation index (NDVI) value in Henan province from 2017 to 2018 within 54 min. Therefore, the experiment demonstrated that the improved row keys can also be applied to store raster data when using HBase. [ABSTRACT FROM AUTHOR]

• A new corn ears dataset with abnormal diversity for two-pathway CNN was established. • The whole corn ears were screened more effectively in actual seed production factory. • A two-pathway CNN was proposed, which has stronger performance than one-way CNN. Screening corn ear is an important and time-consuming task in the process of corn seed production. Recently, Deep Learning plays a major role in learning image features, which has widely used in image classification tasks. In this paper, we propose a novel high-throughput method to screen corn ear at actual seed production factory based on the two-pathway convolution neural network. The two-pathway convolution neural network combined the advantages of VGG-16 and Resnet-50 can greatly reduce input parameters and improve accuracy. Training of the network was performed with the use of an enlarged corn ears dataset, which was acquired by our high-throughput and easy-to-clean image acquisition device. The dataset contains 17,502 corn images, including 6320 normal corn, 5422 rehusk corn and 5760 abnormal corn. The experiments showed that the average classification accuracy was 97.23%. To ensure the superior performance of the proposed two-pathway convolution neural network, we have carried out the experimental comparison with other one-way networks. Also, we explore the impact of network parameters on the classification results. Comprehensive empirical analyses reveal that the proposed method achieves excellent performance and outperforms existing methods in a non-structural environment. [ABSTRACT FROM AUTHOR]

Vegetable mapping from remote sensing imagery is important for precision agricultural activities such as automated pesticide spraying. Multi-temporal unmanned aerial vehicle (UAV) data has the merits of both very high spatial resolution and useful phenological information, which shows great potential for accurate vegetable classification, especially under complex and fragmented agricultural landscapes. In this study, an attention-based recurrent convolutional neural network (ARCNN) has been proposed for accurate vegetable mapping from multi-temporal UAV red-green-blue (RGB) imagery. The proposed model firstly utilizes a multi-scale deformable CNN to learn and extract rich spatial features from UAV data. Afterwards, the extracted features are fed into an attention-based recurrent neural network (RNN), from which the sequential dependency between multi-temporal features could be established. Finally, the aggregated spatial-temporal features are used to predict the vegetable category. Experimental results show that the proposed ARCNN yields a high performance with an overall accuracy of 92.80%. When compared with mono-temporal classification, the incorporation of multi-temporal UAV imagery could significantly boost the accuracy by 24.49% on average, which justifies the hypothesis that the low spectral resolution of RGB imagery could be compensated by the inclusion of multi-temporal observations. In addition, the attention-based RNN in this study outperforms other feature fusion methods such as feature-stacking. The deformable convolution operation also yields higher classification accuracy than that of a standard convolution unit. Results demonstrate that the ARCNN could provide an effective way for extracting and aggregating discriminative spatial-temporal features for vegetable mapping from multi-temporal UAV RGB imagery. [ABSTRACT FROM AUTHOR]

Thermal remote sensing provides a method to describe spatial heterogeneity of the "urban heat island" effect and to evaluate the function of temperature regulation. Rapid urbanization and heatwave events with increasing frequencies need a quantitative analysis on the supply and demand for an urban temperature regulating service, which is a gap in urban heat island (UHI) studies in rapidly urbanizing cities. In order to study the quantitative relationship between landscape metrics (including area index and shape index) and temperature regulating service, this study applied a temperature regulating service in an urban thermal environment study based on the "source–sink" landscape theory in western Shenzhen in different periods. The identification of source and sink landscapes is based on the spatial relationship of unusual surface features derived from Landsat-5 and -8 and the consideration of the temperature difference. We found that the source landscapes at different periods provide temperature regulating services for different distances, which directly lead to the difference between the theoretical service value based on the Alternative Cost Method and the actual service value considering demand, changing in the same trend. The results show that the supply distance of temperature regulating services in 2005, 2010, and 2013 is 150 m, 180 m, and 210 m, respectively. The temperature regulating service value is 3.043, 3.273, and 4.308 billion yuan in 2005, 2010, and 2013, which is lower than the estimation value without considering supply and demand (16.638, 23.728, and 37.495 billion yuan, respectively). The value of the temperature regulating service has a positive correlation with the increase of the patch area index. With the gradual complexity of the shape, the service value increases first and then decreases. Moreover, the landscapes with the smallest shape index and area index have the shortest distance for service supplying. The assessment of the temperature regulating service needs to consider the presence of demand landscapes. Furthermore, the interaction of landscapes under different conditions requires further consideration. The setting of the cooling landscape shape and area for mitigating the "urban heat island" effect can provide references to urban planners and policymakers in the practice of urban climate adaptation and regulation. [ABSTRACT FROM AUTHOR]

The extraction and evaluation of crop production units are important foundations for agricultural production and management in modern smallholder regions, which are very significant to the regulation and sustainable development of agriculture. Crop areas have been recognized efficiently and accurately via remote sensing (RS) and machine learning (ML), especially deep learning (DL), which are too rough for modern smallholder production. In this paper, a delimitation-grading method for actual crop production units (ACPUs) based on RS images was explored using a combination of a mask region-based convolutional neural network (Mask R-CNN), spatial analysis, comprehensive index evaluation, and cluster analysis. Da'an City, Jilin province, China, was chosen as the study region to satisfy the agro-production demands in modern smallholder areas. Firstly, the ACPUs were interpreted from perspectives such as production mode, spatial form, and actual productivity. Secondly, cultivated land plots (C-plots) were extracted by Mask R-CNN with high-resolution RS images, which were used to delineate contiguous cultivated land plots (CC-plots) on the basis of auxiliary data correction. Then, the refined delimitation-grading results of the ACPUs were obtained through comprehensive evaluation of spatial characteristics and real productivity clustering. For the conclusion, the effectiveness of the Mask R-CNN model in C-plot recognition (loss = 0.16, mean average precision (mAP) = 82.29%) and a reasonable distance threshold (20 m) for CC-plot delimiting were verified. The spatial features were evaluated with the scale-shape dimensions of nine specific indicators. Real productivities were clustered by the incorporation of two-step cluster and K-Means cluster. Furthermore, most of the ACPUs in the study area were of a reasonable scale and an appropriate shape, holding real productivities at a medium level or above. The proposed method in this paper can be adjusted according to the changes of the study area with flexibility to assist agro-supervision in many modern smallholder regions. [ABSTRACT FROM AUTHOR]