Search

Wheat (Triticum aestivum L.) leaf rust is the most common and widely distributed wheat disease. Non‐destructive and real‐time methods for monitoring wheat leaf rust can help prevent and control plant diseases in agricultural production. In this study, we obtained multispectral imagery of the wheat canopy acquired by an unmanned aerial vehicle, selected the vegetation index using the K‐means algorithm (KA) and genetic algorithm (GA), and established a wheat leaf rust monitoring model based on the backpropagation neural network (BPNN) method. The results showed that the R2 and RMSE of the KA‐BPNN model were 0.902% and 5.45% for the modeling set, respectively, and 0.784% and 4.76% for the validation set, respectively; and the R2 and RMSE of the GA‐BPNN model was 0.922% and 4.88% for the modeling set, respectively, and 0.780% and 4.28% for the validation set, respectively. The prediction model after optimizing the variables using KA and GA had higher accuracy than the BPNN model, implying that using variable dimensionality reduction methods and complex machine learning algorithms to construct estimation models can improve model accuracy significantly. These models accurately monitored leaf rust in winter wheat, providing a theoretical basis and technical support for assessing plant diseases and screening disease‐resistant wheat varieties. [ABSTRACT FROM AUTHOR]

Grassland aboveground biomass is crucial for evaluating grassland desertification, degradation, and grassland and livestock balance. Given the lack of understanding of mechanical processes and limited simulation accuracy for grassland aboveground biomass estimation, especially at the regional scale, this study investigates a new method combining remote sensing data assimilation technology and a grassland process-based model to estimate regional grassland biomass, focusing on improving the simulation accuracy by modeling and revealing the mechanism interpretability of grassland growth processes. Xilinhot City of Inner Mongolia was used as the study area. The ModVege model was selected as the grass dynamic simulation model. A likelihood function was constructed composed of the LAI, grassland aboveground biomass, and daily measurements wherein the accumulated temperature reached ST2 (the temperature sum defining the end of reproductive growth). Then, the Markov chain Monte Carlo (MCMC) methodology was adapted to calibrate the ModVege model by maximizing the likelihood function. The time-series LAI from MOD15A3H was assimilated into the ModVege model, and the model parameters ST2 and BMGV0 (initial biomass and green vegetative tissues, respectively) were optimized at a 500 m pixel scale based on the four-dimensional variational method (4DVar) method. Compared with August 15th, the RMSE and MAPE of aboveground biomass were 242 kg/ha and 10%, respectively, after calibration. Data assimilation improved this accuracy, with the RMSE decreasing to 214 kg/ha. Overall, the aboveground grassland biomass of Xilinhot City shows spatial distribution patterns of high value in the northeast and low value in the central and southeast areas. Generally, the method implemented in this study provides an important reference for the aboveground biomass estimation of regional grassland. [ABSTRACT FROM AUTHOR]

By virtue of its large-covered spatial information and high-resolution spectral information, hyperspectral images make lots of mapping-based fine-grained remote sensing applications possible. However, due to the inconsistency of land-cover types between different images, most hyperspectral image classification methods keep their effectiveness by training on every image and saving all classification models and training samples, which limits the promotion of related remote sensing tasks. To deal with the aforementioned issues, this paper proposes a hyperspectral image classification method based on class-incremental learning to learn new land-cover types without forgetting the old ones, which enables the classification method to classify all land-cover types with one final model. Specially, when learning new classes, a knowledge distillation strategy is designed to recall the information of old classes by transferring knowledge to the newly trained network, and a linear correction layer is proposed to relax the heavy bias towards the new class by reapportioning information between different classes. Additionally, the proposed method introduces a channel attention mechanism to effectively utilize spatial–spectral information by a recalibration strategy. Experimental results on the three widely used hyperspectral images demonstrate that the proposed method can identify both new and old land-cover types with high accuracy, which proves the proposed method is more practical in large-coverage remote sensing tasks. [ABSTRACT FROM AUTHOR]

Crop classification maps are fundamental data for global change research, regional agricultural regulation, fine production, and insurance services. The key to crop classification is samples, but it is very time-consuming in annual field sampling. Therefore, how to use historical samples in crop classification for future years at a lower cost is a research hotspot. By constructing the spectral feature vector of each historical sample in the historical year and its neighboring pixels in the target year, we produced new samples and classified them in the target year. Specifically, based on environmental similarity, we first calculated the similarities of every two pixels between each historical year and target year and took neighboring pixels with the highest local similarity as potential samples. Then, cluster analysis was performed on those potential samples of the same crop, and the class with more pixels is selected as newly generated samples for classification of the target year. The experiment in Heilongjiang province, China showed that this method can generate new samples with the uniform spatial distribution and that the proportion of various crops is consistent with field data in historical years. The overall accuracy of the target year by the newly generated sample and the real sample is 61.57 and 80.58%, respectively. The spatial pattern of maps obtained by two models is basically the same, and the classification based on the newly generated samples identified rice better. For areas with majority fields having no rotation, this method overcomes the problem of insufficient samples caused by difficulties in visual interpretation and high cost on field sampling, effectively improves the utilization rate of historical samples, and provides a new idea for crop mapping in areas lacking field samples of the target year. [ABSTRACT FROM AUTHOR]

Global oil palm plantations have expanded in the last few decades, resulting in negative impacts on the environment. Satellite remote sensing plays an important role in monitoring the expansion of oil palm plantations, but requires high-quality ground samples for training and validation. To facilitate the monitoring of oil palm plantations on a large scale, we propose an oil palm sample data- base that includes the five countries with the largest areas of oil palm plantations: Indonesia, Malaysia, Nigeria, Thailand, and Ghana. In total, 45,896 samples were collected using a hexagonal sampling design. High-resolution images from Google Earth, the Advanced Land Observing Satellite (ALOS) Phased Array type L-band Synthetic Aperture Radar (PALSAR) images, and Landsat optical images were used to identify oil palm plantations and other types of land cover (croplands, forests, grasslands, shrublands, water, hard surfaces, and bare land). The characteristics of oil palm cover and its environment, including PALSAR backscattering coefficients, terrain, and climate recorded in this database are also discussed. The results indicate that using the PALSAR band algebra threshold alone is not recommended to distinguish oil palm from other land-cover/use types. [ABSTRACT FROM AUTHOR]

Remote sensing based land cover mapping at large scale is time consuming when using either supervised or unsupervised classification approaches. This article used a fast clustering method-Clustering by Eigen Space Transformation (CBEST) to produce a land cover map for China. Firstly, 508 Landsat TM scenes were collected and processed. Then, TM images were clustered by combining CBEST and K-means in each pre-defined ecological zone (50 in total for China). Finally, the obtained clusters were visually interpreted as land cover types to complete a land cover map. Accuracy evaluation using 2159 test samples indicates an overall accuracy of 71.7% and a Kappa coefficient of 0.64. Comparisons with two global land cover products (i.e., Finer Resolution Observation and Monitoring of Global Land Cover (FROM-GLC) and GlobCover 2009) also indicate that our land cover result using CBEST is superior in both land cover area estimation and visual effect for different land cover types. [ABSTRACT FROM AUTHOR]

Since the launch of the first land-observation satellite (Landsat-1) in 1972, land-cover mapping has accumulated a wide range of knowledge in the peer-reviewed literature. However, this knowledge has never been comprehensively analysed for new discoveries. Here, we developed the first spatialized database of scientific literature in English about land-cover mapping. Using this database, we tried to identify the spatial temporal patterns and spatial hotspots of land-cover mapping research around the world. Among other findings, we observed (1) a significant mismatch between hotspot areas of land-cover mapping and areas that are either hard to map or rich in biodiversity; (2) mapping frequency is positively related to economic conditions; (3) there is no obvious temporal trend showing improvement in mapping accuracy; (4) images with more spectral bands or a combination of data types resulted in increased mapping accuracies; (5) accuracy differences due to algorithm differences are not as large as those due to various types of data used; and (6) the complexity of a classification system decreases its mapping accuracy. We recommend that one way to improve our understanding of the challenges, advances, and applications of previous land-cover mapping is for journals to require area-based information at the time of manuscript submission. In addition, building a standard protocol for systematic assessment of land-cover mapping efforts at the global scale through international collaboration is badly needed. [ABSTRACT FROM PUBLISHER]

Remote sensing images can be used to delineate variations in the area of lakes and to assess the influence of environmental changes and human activities. However, because lakes are dynamic, results obtained from individual images acquired on a single date are not representative and do not accurately reflect ongoing changes. In this study, we used 8-day moderate resolution imaging spectroradiometer (MODIS) composite data from 2000 to 2010 to map water surface changes over 629 lakes in China. We combined automatic extraction of training data and support vector machine classification to derive the spatial distribution of these large water bodies. The producer's and user's accuracies for MODIS images were 91.06 % and 89.81 %, respectively, when compared with interpretation results from 30 m resolution Landsat images taken on similar days. Area changes, variability, inundation intensity, and rainy seasons of the 629 lakes were analyzed based on this multi-temporal lake database. The total area of the 629 lakes increased over the study period, primarily as a result of the expansion of lake areas on the Tibetan Plateau. There were 12 lakes with a maximum area >1,000 km, and six of these decreased in area from 2000 to 2010. The shrinkages of Poyang Lake and Dongting Lake were −54.76 and −25.08 km/a, respectively. The area of lakes on Tibetan Plateau, in northern Xinjiang, northeastern Inner Mongolia, and northeastern China varied little, while lakes on the Yangtze Plain, in southern Inner Mongolia, and central Xinjiang fluctuated considerably. Inundation intensity increased for lakes on the Tibetan Plateau, in northern Xinjiang, Heilongjiang, and Jilin, while inundation extent decreased in central Xinjiang, southern Tibet, southern Inner Mongolia, Sichuan, and on the Yangtze Plain. This study is an attempt to develop high-frequency specific land cover maps to improve applicability of general land cover maps. The lake products serve as an important supplement to hydrologic data. The lake database enables the generation of new land surface process models, which could improve the precision of simulations, based on more accurate observations of dynamic lake systems. [ABSTRACT FROM AUTHOR]

Grasslands, as an important part of terrestrial ecosystems, are facing serious threats of land degradation. Therefore, the remote monitoring of grasslands is an important tool to control degradation and protect grasslands. However, the existing methods are often disturbed by clouds and fog, which makes it difficult to achieve all-weather and all-time grassland remote sensing monitoring. Synthetic aperture radar (SAR) data can penetrate clouds, which is helpful for solving this problem. In this study, we verified the advantages of the fusion of multi-spectral (MS) and SAR data for improving classification accuracy, especially for cloud-covered areas. We also proposed an adaptive feature fusion method (the SK-like method) based on an attention mechanism, and tested two types of patch construction strategies, single-size and multi-size patches. Experiments have shown that the proposed SK-like method with single-size patches obtains the best results, with 93.12% accuracy and a 0.91 average f1-score, which is a 1.02% accuracy improvement and a 0.01 average f1-score improvement compared with the commonly used feature concatenation method. Our results show that the all-weather, all-time remote sensing monitoring of grassland is possible through the fusion of MS and SAR data with suitable feature fusion methods, which will effectively enhance the regulatory capability of grassland resources. [ABSTRACT FROM AUTHOR]

Time series of vegetation index (VI) information derived from remote sensing is important for land-cover change detection. Although traditional change vector analysis (TCVA) is an effective method for extracting land-cover change information from a time series of VI data, it has the disadvantage of being too sensitive to temporal fluctuations in VI values. The method tends to overestimate the changes and confuse the actual land-cover conversion with the land covers that have not been converted but experience significant VI changes. Cross-correlogram spectral matching (CCSM) can tell the degree of shape similarity between VI profiles and be used to detect land-cover conversion. However, this method may omit some land conversion in which the before and after land-cover types are rather similar in VI profile shape but differ significantly in absolute VI values. This article proposes a new approach that improves TCVA with an adapted use of CCSM. First, TCVA is employed for preliminary detection of land-cover changes. Second, the changes caused by temporal fluctuations of VI values are identified through the CCSM analysis and excluded to only keep the most likely land-cover conversions. Finally, classification is performed to map the different types of land-cover conversions. The improved change vector analysis (ICVA) was applied to detect land-cover conversions from 2000 to 2008, using a time series of Moderate Resolution Imaging Spectroradiometer (MODIS) enhanced VI images for the Beijing–Tianjin–Tangshan urban agglomeration district, China. The results show that ICVA is able to detect land-cover conversion with a significantly higher accuracy (78.00%, κ = 0.56) than TCVA (64.00%, κ = 0.35) or CCSM (66.60%, κ = 0.27). The proposed approach is of particular value in distinguishing actual land-cover conversion from land-cover modifications resulting from phenological changes. [ABSTRACT FROM PUBLISHER]

The accurate and timely access to the spatial distribution information of crops is of great importance for agricultural production management. Although widely used, supervised classification mapping requires a large number of field samples, and is consequently costly in terms of time and money. In order to reduce the need for sample size, this paper proposes an unsupervised classification method based on principal components isometric binning (PCIB). In particular, principal component analysis (PCA) dimensionality reduction is applied to the classification features, followed by the division of the top k principal components into equidistant bins. Bins of the same category are subsequently merged as a class label. Multitemporal Gaofen 1 satellite (GF-1) remote sensing images were collected over the southwest of Hulin City and Luobei County of Hegang City, Heilongjiang Province, China in order to map crop types in 2016 and 2017. Our proposed method was compared with commonly used classifiers (random forest, K-means and Iterative Self-Organizing Data Analysis Techniques Algorithm (ISODATA)). Results demonstrate PCIB and random forest to have the highest classification accuracies, reaching 82% in 2016 in the southwest of Hulin City. In Luobei County in 2016, the accuracies of PCIB and random forest were determined as 81% and 82%, respectively. It can be concluded that the overall accuracy of our proposed method meets the basic requirements of classification accuracy. Despite exhibiting a lower accuracy than that of random forest, PCIB does not require a large field sample size, thus making it more suitable for large-scale crop mapping. [ABSTRACT FROM AUTHOR]

Large-scale crop mapping provides important information in agricultural applications. However, it is a challenging task due to the inconsistent availability of remote sensing data caused by the irregular time series and limited coverage of the images, together with the low spatial resolution of the classification results. In this study, we proposed a new efficient method based on grids to address the inconsistent availability of the high-medium resolution images for large-scale crop classification. First, we proposed a method to block the remote sensing data into grids to solve the problem of temporal inconsistency. Then, a parallel computing technique was introduced to improve the calculation efficiency on the grid scale. Experiments were designed to evaluate the applicability of this method for different high-medium spatial resolution remote sensing images and different machine learning algorithms and to compare the results with the widely used nonparallel method. The computational experiments showed that the proposed method was successful at identifying large-scale crop distribution using common high-medium resolution remote sensing images (GF-1 WFV images and Sentinel-2) and common machine learning classifiers (the random forest algorithm and support vector machine). Finally, we mapped the croplands in Heilongjiang Province in 2015, 2016, 2017, which used a random forest classifier with the time series GF-1 WFV images spectral features, the enhanced vegetation index (EVI) and normalized difference water index (NDWI). Ultimately, the accuracy was assessed using a confusion matrix. The results showed that the classification accuracy reached 88%, 82%, and 85% in 2015, 2016, and 2017, respectively. In addition, with the help of parallel computing, the calculation speed was significantly improved by at least seven-fold. This indicates that using the grid framework to block the data for classification is feasible for crop mapping in large areas and has great application potential in the future. [ABSTRACT FROM AUTHOR]

Accurate and timely crop classification results play a crucial role in providing data support for agricultural policy-making and crop yield estimation. However, the current development of crop classification faces a bottleneck in improving classification performance due to limited labeled samples and saturated classification algorithms. In this study, we propose a novel method to improve crop classification performance by leveraging unlabeled remote sensing data (URSD). Importantly, our method does not necessitate a large number of labeled samples or significant modifications to the classification algorithm. Instead, it relies on a unique self-supervised training approach and a substantial amount of URSD. Specifically, we develop a self-supervised classification framework based on a Multilayer Perceptron (MLP) and introduce a self-supervised training approach that takes into account both temporal and spectral factors. Additionally, we construct a historical sample classification model based on crop growth knowledge, emphasizing the correlation of local time series. We evaluate the proposed method using four study areas in China. The analysis of pre-training data types reveals that our method not only improves the classification performance of current year samples but also demonstrates noticeable improvement in classifying historical samples. The classification method analysis demonstrates the ability of our proposed self-supervised learning training approach to accumulate more prior knowledge. Overall, these results highlight the advantages of our method in terms of classification efficiency and performance improvement. [ABSTRACT FROM AUTHOR]