Search

The European Union and the European Space Agency (EU/ESA) have promoted since 1998 (Baveno Manifesto*) the GMES Programme (Global Monitoring for Environment and Security), nowadays called Copernicus (www.copernicus.eu). In the agriculture domain, the use of Copernicus Sentinel imagery and its services are providing several new opportunities. The knowledge of fundamentals of Earth Observation/Geographic Information EO/GI, namely Geomatics, for the development of innovative strategies for professional skills adequacy and capacity building, supporting Copernicus user uptake, becomes mandatory (Gomarasca, 2009). The target is to help bridging gaps between supply and demand of education and training for geospatial sector (www.eo4geo.eu). The innovative and strategical novelties are the complete free access to Sentinel time series imagery and digital image processing software "Sentinel toolboxes" such as SNAP (Sentinel Application Platform) for different environments (Windows, Mac, Unix). The paper introduce topics as crop mapping and monitoring, biophysical parameters, phenology and yield estimations, through several concluded or ongoing international projects such as: ERMES -FP7 (http://www.ermes-fp7space.eu/it/homepage/, Busetto et al. 2017) and SATURNO (https://www.progettosaturno.it/, Nutini et al., 2018) devoted to the regional agricultural monitoring. As conclusion, SNAP software for image processing of Sentinel data was demonstrated and tested together with Earth Engine software for specific vertical agriculture applications. The topics reported in this paper have been part of the Summer School 'Sentinel for Applications in Agriculture' supported by the Copernicus programme, several scientific associations (AIT, ASITA, EARSeL - European Association of Remote Sensing Laboratories), the European Erasmus+ project EO4GEO, University Departments and Geo-Information Companies. [ABSTRACT FROM AUTHOR]

The paper presents multi-sensor applications of Unmanned Aerial Vehicles (UAVs) on three different cases of study, belonging to the wide category of Cultural Heritage (CH). The contribution aims to examine the efficacy of different methodological approach of surveys made in VIS and TIR range with aerial platforms. The use of UAV on two archaeological areas, Çatalhöyük site (Konya, Turkey) and the Medicean Villa of Pratolino (Florence, Italy) and an application of precision agriculture in Lamole (Greve in Chianti, Italy) will be presented. In particular, the analysis will focus on the accuracy of the obtained data, in terms of both metric and image quality, the possible information to extract from the IR imaging, the relationship between costs and benefits and the total amount of information that can be gained. The two different fields of research (archaeological and agricultural one) show that there are some similarities in the approaches and which could be the improving to obtain using the aerial survey in the visual and IR bands. [ABSTRACT FROM AUTHOR]

The present paper aims to understand the spatio-temporal dynamics of the Brahmaputra river islands locally known as chars in Assam for agriculture crop expansion using long term multispectral satellite data and Google Earth Engine. This study also provides information on existing agriculture lands on these chars. For the study Landsat data is analysed to find the long term stable islands (1988–2018) and the present status of these islands for seasonal crop expansion. Validation of results was performed by using high-resolution satellite data. It is found that total area of vegetative chars has increased in past three decades and approximately 146 thousand hectares area of char is stable from past ten years. This study also reveals that the major crop cultivation is in Lower Brahmaputra Valley (LBV). In Upper Brahmaputra Valley (UBV), the crop cultivation is almost negligible compared to the large islands size. It can be inferred that less stable chars which are mostly located in upper Assam has negligible agriculture. It is also observed that at many places in lower Assam, double cropping system is followed. This study can be further extended by including factors like soil type, soil texture, rainfall, socio-economic etc. to study suitability for different crops. Proper facilities and incentives are to be provided to farmers of this region for better food security. [ABSTRACT FROM AUTHOR]

The accurate determination of the quality parameters of crops requires a spectral range from 400 nm to 2500 nm (Kawamura et al., 2010, Thenkabail et al., 2002). Presently the hyperspectral imaging systems that cover this wavelength range consist of several separate hyperspectral imagers and the system weight is from 5 to 15 kg. In addition the cost of the Short Wave Infrared (SWIR) cameras is high (∼50 k€). VTT has previously developed compact hyperspectral imagers for drones and Cubesats for Visible and Very near Infrared (VNIR) spectral ranges (Saari et al., 2013, Mannila et al., 2013, Näsilä et al., 2016). Recently VTT has started to develop a hyperspectral imaging system that will enable imaging simultaneously in the Visible, VNIR, and SWIR spectral bands. The system can be operated from a drone, on a camera stand, or attached to a tractor. The targeted main applications of the DroneKnowledge hyperspectral system are grass, peas, and cereals. In this paper the characteristics of the built system are shortly described. The system was used for spectral measurements of wheat, several grass species and pea plants fixed to the camera mount in the test fields in Southern Finland and in the green house. The wheat, grass and pea field measurements were also carried out using the system mounted on the tractor. The work is part of the Finnish nationally funded "DroneKnowledge - Towards knowledge based export of small UAS remote sensing technology" project. [ABSTRACT FROM AUTHOR]

This paper presents some preliminary results from research on monitoring the urban growth of Shenzhen in China. Agriculture is still the pillar of national economies in many countries including China. Thus, agriculture contributes to population growth. Population growth follows either exponential or logistic growth models. These models can be examined using a time-series of geospatial data, mainly historical earth observation imagery from satellites such as LANDSAT. Such multitemporal data may provide insights into settlement analysis as well as on population dynamics and hence, quantify the loss of agricultural land. In this study, LANDSAT data of ten dates, at approximately five yearly intervals from 1977 to 2017 were used. The remote sensing techniques used for analysis of data for 40 years were image selection, then followed by geometric and radiometric corrections and mosaicking. Also, classification, remote sensing image fusion, and change detection methods were used. This research extracted the information on the amount, direction, and speed of urbanization, and hence, the number of hectares of agricultural land lost due to urban expansion. Several specific elements were used in the descriptive model of landscape changes and population dynamics of the city of Shenzhen in China. These elements are: i) quantify the urban changes, from a small town (37.000 people in the early 1970's) to the megalopolis of around 20 million habitants today. ii) Examining the rate of urban extension on the loss of agricultural landscape and population growth. iii) The loss of food production was analysed against the economic growth in the region. iv) The aspects of loss of agricultural land, area of built-up urban land, and increase in population are studied quantitatively, by the temporal analysis of earth observation geospatial data. The experimental results from this study show that the proposed method is effective in determining loss of agricultural land in any city due to urbanization. It can be used by town planner and other stakeholders such as land surveyors and agriculture experts to mitigate the mushrooming of unplanned settlements in many town / villages and loss of land for agriculture which might cause problems in food security. [ABSTRACT FROM AUTHOR]

The accuracy of supervised image classification is highly dependent upon several factors such as the design of training set (sample selection, composition, purity and size), resolution of input imagery and landscape heterogeneity. The design of training set is still a challenging issue since the sensitivity of classifier algorithm at learning stage is different for the same dataset. In this paper, the classification of RapidEye imagery with balanced and imbalanced training data for mapping the crop types was addressed. Classification with imbalanced training data may result in low accuracy in some scenarios. Support Vector Machines (SVM), Maximum Likelihood (ML) and Artificial Neural Network (ANN) classifications were implemented here to classify the data. For evaluating the influence of the balanced and imbalanced training data on image classification algorithms, three different training datasets were created. Two different balanced datasets which have 70 and 100 pixels for each class of interest and one imbalanced dataset in which each class has different number of pixels were used in classification stage. Results demonstrate that ML and NN classifications are affected by imbalanced training data in resulting a reduction in accuracy (from 90.94% to 85.94% for ML and from 91.56% to 88.44% for NN) while SVM is not affected significantly (from 94.38% to 94.69%) and slightly improved. Our results highlighted that SVM is proven to be a very robust, consistent and effective classifier as it can perform very well under balanced and imbalanced training data situations. Furthermore, the training stage should be precisely and carefully designed for the need of adopted classifier. [ABSTRACT FROM AUTHOR]

In this paper we investigate the performance of new light-weight multispectral sensors for micro UAV and their application to selected tasks in agronomical research and agricultural practice. The investigations are based on a series of flight campaigns in 2014 and 2015 covering a number of agronomical test sites with experiments on rape, barley, onion, potato and other crops. In our sensor comparison we included a high-end multispectral multiSPEC 4C camera with bandpass colour filters and reference channel in zenith direction and a low-cost, consumer-grade Canon S110 NIR camera with Bayer pattern colour filters. Ground-based reference measurements were obtained using a terrestrial hyperspectral field spectrometer. The investigations show that measurements with the high-end system consistently match very well with ground-based field spectrometer measurements with a mean deviation of just 0.01-0.04 NDVI values. The low-cost system, while delivering better spatial resolutions, expressed significant biases. The sensors were subsequently used to address selected agronomical questions. These included crop yield estimation in rape and barley and plant disease detection in potato and onion cultivations. High levels of correlation between different vegetation indices and reference yield measurements were obtained for rape and barley. In case of barley, the NDRE index shows an average correlation of 87% with reference yield, when species are taken into account. With high geometric resolutions and respective GSDs of down to 2.5 cm the effects of a thrips infestation in onion could be analysed and potato blight was successfully detected at an early stage of infestation. [ABSTRACT FROM AUTHOR]

In this paper the development of a lightweight and highly modularized airborne sensor platform for remote sensing applications utilizing a gyrocopter as a carrier platform is described. The current sensor configuration consists of a high resolution DSLR camera for VIS-RGB recordings. As a second sensor modality, a snapshot hyperspectral camera was integrated in the aircraft. Moreover a custom-developed thermal imaging system composed of a VIS-PAN camera and a LWIR-camera is used for aerial recordings in the thermal infrared range. Furthermore another custom-developed highly flexible imaging system for high resolution multispectral image acquisition with up to six spectral bands in the VIS-NIR range is presented. The performance of the overall system was tested during several flights with all sensor modalities and the precalculated demands with respect to spatial resolution and reliability were validated. The collected data sets were georeferenced, georectified, orthorectified and then stitched to mosaics. [ABSTRACT FROM AUTHOR]

The Philippines embarked on a nationwide mapping endeavour through the Disaster Risk and Exposure Assessment for Mitigation (DREAM) Program of the University of the Philippines and the Department of Science and Technology (DOST). The derived accurate digital terrain models (DTMs) are used in flood models to generate risk maps and early warning system. With the availability of LiDAR data sets, the Phil-LiDAR 2 program was conceptualized as complementary to existing programs of various national government agencies and to assist local government units. Phil-LiDAR 2 aims to provide an updated natural resource inventory as detailed as possible using LiDAR point clouds, LiDAR derivative products, orthoimages and other RS data. The program assesses the following natural resources over a period of three years from July 2014: agricultural, forest, coastal, water, and renewable energy. To date, methodologies for extracting features from LiDAR data sets have been developed. The methodologies are based on a combination of object-based image analysis, pixel-based image analysis, optimization of feature selection and parameter values, and field surveys. One of the features of the Phil-LiDAR 2 program is the involvement of fifteen (15) universities throughout the country. Most of these do not have prior experience in remote sensing and mapping. With such, the program has embarked on a massive training and mentoring program. The program is producing more than 200 young RS specialists who are protecting the environment through RS and other geospatial technologies. This paper presents the program, the methodologies so far developed, and the sample outputs. [ABSTRACT FROM AUTHOR]

Remote sensing is a suitable tool for estimating the spatial variability of crop canopy characteristics, such as canopy chlorophyll content (CCC) and green ground cover (GGC%), which are often used for crop productivity analysis and site-specific crop management. Empirical relationships exist between different vegetation indices (VI) and CCC and GGC% that allow spatial estimation of canopy characteristics from remote sensing imagery. However, the use of VIs is not suitable for an operational production of CCC and GGC% maps due to the limited transferability of derived empirical relationships to other regions. Thus, the operational value of crop status maps derived from remotely sensed data would be much higher if there was no need for reparametrization of the approach for different situations. This paper reports on the suitability of high-resolution RapidEye data for estimating crop development status of winter wheat over the growing season, and demonstrates two different approaches for mapping CCC and GGC%, which do not rely on empirical relationships. The final CCC map represents relative differences in CCC, which can be quickly calibrated to field specific conditions using SPAD chlorophyll meter readings at a few points. The prediction model is capable of predicting SPAD readings with an average accuracy of 77%. The GGC% map provides absolute values at any point in the field. A high R² value of 80% was obtained for the relationship between estimated and observed GGC%. The mean absolute error for each of the two acquisition dates was 5.3% and 8.7%, respectively. [ABSTRACT FROM AUTHOR]

Rice acreage estimation is a key aspect to guarantee food security and also important to support government agricultural subsidy system. In this paper, we explored a sophisticated method to improve rice estimation accuracy at county scale and we developed our approach with China Environment Satellite HJ-1A/B data in Hunan Province, a fragmented area with complex rice cropping patterns. Our approach improved the estimation accuracy by combing supervised and unsupervised classification upon decomposition of mixed pixels model, and the rice estimation results, validated by ground survey data, showed a close relationship (RMSE≈3.40) with survey figures, the estimated accuracy (EA) reached 83.74% at county level according to the sub-pixel method, and the accuracy can be increased about 12% compared to the pure-pixel method. The results suggest that decomposition of mixed pixels method has great significance to the improvement of rice acreage estimation accuracy, and can be used in mountainous and broken planting area. [ABSTRACT FROM AUTHOR]

The Copernicus Global Land service provides continuously a set of bio-geophysical variables describing, over the whole globe, the vegetation dynamic, the energy budget at the continental surface and some components of the water cycle. These generic products serve numerous applications including agriculture and food security monitoring. The portfolio of the Copernicus Global Land service contains Essential Climate Variables like the Leaf Area Index (LAI), the Fraction of PAR absorbed by the vegetation (FAPAR), the surface albedo, the Land Surface Temperature, the soil moisture, the burnt areas, the areas of water bodies, and additional vegetation indices. They are generated every hour, every day or every 10 days on a reliable automatic basis from Earth Observation satellite data. Beside this timely production, the available historical archives have been processed, using the same innovative algorithms, to get consistent time series as long as possible. All products are accessible, free of charge after registration through FTP/HTTP (http://land.copernicus.eu/global/) and through the GEONETCast satellite distribution system. The evolution of the service towards the operations at 333m resolution is partly supported by the FP7/ImagineS project which focuses on the retrieval of LAI, FAPAR, fraction of vegetation cover and surface albedo from PROBA-V sensor data. The paper presents the innovations of the 333m biophysical products, make an overview of their current status, and introduce the next steps of the evolution of the Copernicus Global Land service. [ABSTRACT FROM AUTHOR]

Detection of crop stress from hyperspectral images is of high importance for breeding and precision crop protection. However, the continuous monitoring of stress in phenotyping facilities by hyperspectral imagers produces huge amounts of uninterpreted data. In order to derive a stress description from the images, interpreting algorithms with high prediction performance are required. Based on a static model, the local stress state of each pixel has to be predicted. Due to the low computational complexity, linear models are preferable. In this paper, we focus on drought-induced stress which is represented by discrete stages of ordinal order. We present and compare five methods which are able to derive stress levels from hyperspectral images: One-vs.-one Support Vector Machine (SVM), one-vs.-all SVM, Support Vector Regression (SVR), Support Vector Ordinal Regression (SVORIM) and Linear Ordinal SVM classification. The methods are applied on two data sets - a real world set of drought stress in single barley plants and a simulated data set. It is shown, that Linear Ordinal SVM is a powerful tool for applications which require high prediction performance under limited resources. It is significantly more efficient than the one-vs.-one SVM and even more efficient than the less accurate one-vs.-all SVM. Compared to the very compact SVORIM model, it represents the senescence process much more accurate. [ABSTRACT FROM AUTHOR]

Climate change and increase of extreme weather events, besides the numerous consequences, affect significantly and put in risk the agriculture sectors. Natural disasters, such as floods and wildfires, are responsible for a great loss in agriculture production. National governments together with international bodies make an important effort to cooperate towards the response and resilience when a disaster occurs. In this frame the European Earth Observation Programme - Copernicus provides a series of observation data, in-situ measurements and services related, amongst others, to different types of disasters. Concerning the availability of this big volume of observation data, the aim of DiAS (Disaster and Agriculture Sentinel Applications) project is to revise the existing knowledge on remote sensing methods for mapping the extent of natural and/or man-made disaster over agricultural areas and propose improvements. The developed methodology will be implemented in a Decision Support System (DSS), which will be freely available and easy-to-use by non-experts. In this paper, the developed methodology focuses on mapping floods over agricultural areas. Sentinel-1 and Sentinel-2 imagery are used as input information for the comparison analysis before and after the event. The reference for results' evaluation is the corresponding information delivered by Copernicus Emergency Management Service (EMS). Although, the evaluation results are in good agreement when they could be used, a reference of higher accuracy is needed in order to estimate accurately the quality of the output products. [ABSTRACT FROM AUTHOR]

Activities have focused on using the Landsat time-series and Sentinel-2 datasets to monitor land cover dynamics across the United Kingdom, with mapping of specific areas including missions such as Worldview and Kompsat. This short conference paper shows some of the preliminary results from the Landsat Operational Land Imager, Thematic Mapper and Enhanced Thematic Mapper data processing that has included the development of a pre-processing system that includes cloud masking and an atmospheric correction. The results are promising, but further research is needed. [ABSTRACT FROM AUTHOR]

Accurate crops classification remains a challenging task due to the same crop with different spectra and different crops with same spectrum phenomenon. Recently, UAV-based remote sensing approach gains popularity not only for its high spatial and temporal resolution, but also for its ability to obtain spectraand spatial data at the same time. This paper focus on how to take full advantages of spatial and spectrum features to improve crops classification accuracy, based on an UAV platform equipped with a general digital camera. Texture and spatial features extracted from the RGB orthoimage and the digital surface model of the monitoring area are analysed and integrated within a SVM classification framework. Extensive experiences results indicate that the overall classification accuracy is drastically improved from 72.9% to 94.5% when the spatial features are combined together, which verified the feasibility and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Recent advances in cloud-based technology has led to the rapid increase of geospatial web-based applications. The combination of GIS and cloud-based solutions is revolutionizing product development in the geospatial industry and is facilitating accessibility to a wider range of users, planners and decision makers. Accessible through an internet browser, web applications are an effective and convenient method to disseminate information in multiple formats, and they provide an interface offering interactive access to geospatial data, real-time integration and data processing, and application specific analysis tools. An example of such a web application is GeoTerraImage's monthly crop monitoring tool called GeoFarmer. This tool uses climatic data and satellite imagery processed through a complex rule-based algorithms to determine monthly climatic averages and anomalies, and most importantly the field specific crop status (i.e. is the field fallow, or is the crop emerging, or if the field has been harvested). Monthly field verification has formed a part of calibrating the growth classification outputs to further improve the accuracy of its monthly agricultural reporting. The goal of this application is to provide timely data to decision makers to assist them in field-level and regional crop growth monitoring, crop production and management, financial risk assessment and insurance, and food security applications. This web application has the unique advantage of being highly transportable to other regions, since it has been designed so it can easily be adapted to other seasonal growth response patterns, and up-scaled to regional or national coverages for operational use. [ABSTRACT FROM AUTHOR]

Benefiting from the high cadence and spatial resolution of the new generation of Earth observation satellites, remote sensing technology is allowing us to derive more valuable information for the agricultural sector. Crop classification is one of the fundamental information derivatives from Earth observation data researchers used for food security, crop monitoring, and economic assessment. The robustness of a crop classification model to variations in environmental and management conditions due to time and location is one of the crucial requirements. To achieve this, we developed a novel self-supervised method using the advantage of unlabeled samples and transformer architectures. We used six different areas in Germany and four years to evaluate the robustness of the model. Our experiments showed that self-supervised deep learning methods could provide a significant advantage in handling these variations. In some cases, we observed around 30 percentage points improvements in F1-score performance compared to a Random Forest based model. [ABSTRACT FROM AUTHOR]

Precision agriculture (PA) is defined as an agricultural management based on the observation, measurement, and response of a set of quantitative and qualitative variables that affects agricultural production. The first step in the approach to precision agriculture is, therefore, the acquisition and collection of data from optical, multispectral, geophysical sensors, etc. aimed at obtaining knowledge and monitoring of the crop. In recent years UAVs are assuming an important role in precision agriculture. The possibility of mounting RGB, multispectral, LiDAR sensors on them make these systems fast, accurate, and usability compared other geomatic methods. In this study, we focus on a very low-cost UAV system to assess individual tree height and generate 3D Model and orthophoto of the study area. We used the DJI Mini2, a low-cost UAV that can be used without a flight rating and without restrictions due to its light weight of only 250 grams. The case study where the survey was performed is an agricultural area of about 1 hectare, where are some fruit trees and a small vineyard. The area was selected because it contained both tall and small trees. The study concerned the influence of the relative flight altitude and therefore of the GSD of the images on the extraction of the dimensional data of the trees. From the results obtained, it can be stated that the flight altitude has certainly more influence on the measurement of small tree (around one meter tall) compared to tall ones (around 4 m). [ABSTRACT FROM AUTHOR]

Soil subsurface moisture content, especially in the root zone, is important for evaluation the influence of soil moisture to agricultural crops. Conservative monitoring by point-measurement methods is time-consuming and expensive. In this paper we represent an active remote-sensing tool for subsurface spatial imaging and analysis of electromagnetic physical properties, mostly water content, by ground-penetrating radar (GPR) reflection. Combined with laboratory methods, this technique enables real-time and highly accurate evaluations of soils' physical qualities in the field. To calculate subsurface moisture content, a model based on the soil texture, porosity, saturation, organic matter and effective electrical conductivity is required. We developed an innovative method that make it possible measures spatial subsurface moisture content up to a depth of 1.5 m in agricultural soils and applied it to two different unsaturated soil types from agricultural fields in Israel: loess soil type (Calcic haploxeralf), common in rural areas of southern Israel with about 30% clay, 30% silt and 40% sand, and hamra soil type (Typic rhodoxeralf), common in rural areas of central Israel with about 10% clay, 5% silt and 85% sand. Combined field and laboratory measurements and model development gave efficient determinations of spatial moisture content in these fields. The environmentally friendly GPR system enabled nondestructive testing. The developed method for measuring moisture content in the laboratory enabled highly accurate interpretation and physical computing. Spatial soil moisture content to 1.5 m depth was determined with 1-5% accuracy, making our method useful for the design of irrigation plans for different interfaces. [ABSTRACT FROM AUTHOR]

The water scarcity crises in the world and specifically in Iran, requires the proper management of this valuable resource. According to the official reports, around 90 percent of the water in Iran is used for agriculture. Therefore, the adequate management and usage of water in this section can help significantly to overcome the above crises. The most important aspect of agricultural water management is related to the irrigation planning, which is basically an allocation problem. The proper allocation of water to the farms is not a simple and trivial problem, because of the limited amount of available water, the effect of different parameters, nonlinear characteristics of the objective function, and the wideness of the solution space. Usually To solve such complex problems, a meta-heuristic method such as genetic algorithm could be a good candidate. In this paper, Genetic Algorithm (GA) is used for the allocation of different amount of water to a number of farms. In this model, the amount of water transferable using canals of level one, in one period of irrigation is specified. In addition, the amount of water required by each farm is calculated using crop type, stage of crop development, and other parameters. Using these, the water production function of each farm is determined. Then, using the water production function, farm areas, and the revenue and cost of each crop type, the objective function is calculated. This objective function is used by GA for the allocation of water to the farms. The objective function is defined such that the economical profit extracted from all farms is maximized. Moreover, the limitation related to the amount of available water is considered as a constraint. In general, the total amount of allocated water should be less than the finally available water (the water transferred trough the level one canals). Because of the intensive scarcity of water, the deficit irrigation method are considered. In this method, the planning is on the basis of the optimum and limited allocation of water, and not on the basis of the each crop water requirement. According to the available literature, in the condition of water scarcity, the implementation of deficit irrigation strategy results in higher economical income. The main difference of this research with others is the allocation of water to the farms. Whilst, most of similar researches concentrate on the allocation of water to different water consumption sections (such as agriculture, industry etc.), networks and crops. Using the GA for the optimization of the water allocation, proper solutions were generated that maximize the total economical income in the entire study area. In addition, although the search space was considerably wide, the results of the implementation showed an adequate convergence speed. The repeatability test of the algorithm also proved that the algorithm is reasonably stable. In general the usage of GA algorithm can be considered as an efficient and trustable method for such irrigation planning problems. By optimum allocation of the water to the farms with different areas and crop types, and considering the deficit irrigation method, the general income of the entire area can be improved substantially. [ABSTRACT FROM AUTHOR]

Wheat is the most widely grown crop globally and an essential source of calories in human diets. Maintaining and increasing global wheat production is therefore strongly linked to food security. In this paper, the evaluation model of winter wheat potential productivity was proposed based on agro-ecological zone and the historical winter wheat yield data in recent 30 years (1983-2011) obtained from FAO. And the potential productions of winter wheat in the world were investigated. The results showed that the realistic potential productivity of winter wheat in Western Europe was highest and it was more than 7500 kg/hm². The realistic potential productivity of winter wheat in North China Plain were also higher, which was about 6000 kg/hm². However, the realistic potential productivity of winter wheat in the United States which is the main winter wheat producing country were not high, only about 3000 kg/hm². In addition to these regions which were the main winter wheat producing areas, the realistic potential productivity in other regions of the world were very low and mainly less than 1500 kg/hm², like in southwest region of Russia. The gaps between potential productivity and realistic productivity of winter wheat in Kazakhstan and India were biggest, and the percentages of the gap in realistic productivity of winter wheat in Kazakhstan and India were more than 40%. In Russia, the gap between potential productivity and realistic productivity of winter wheat was lowest and the percentage of the gap in realistic productivity of winter wheat in Russia was only 10%. [ABSTRACT FROM AUTHOR]

Shape is one of the most important traits of agricultural products due to its relationships with the quality, quantity, and value of the products. For strawberries, the nine types of fruit shape were defined and classified by humans based on the sampler patterns of the nine types. In this study, we tested the classification of strawberry shapes by machine learning in order to increase the accuracy of the classification, and we introduce the concept of computerization into this field. Four types of descriptors were extracted from the digital images of strawberries: (1) the Measured Values (MVs) including the length of the contour line, the area, the fruit length and width, and the fruit width/length ratio; (2) the Ellipse Similarity Index (ESI); (3) Elliptic Fourier Descriptors (EFDs), and (4) Chain Code Subtraction (CCS). We used these descriptors for the classification test along with the random forest approach, and eight of the nine shape types were classified with combinations of MVs + CCS + EFDs. CCS is a descriptor that adds human knowledge to the chain codes, and it showed higher robustness in classification than the other descriptors. Our results suggest machine learning's high ability to classify fruit shapes accurately. We will attempt to increase the classification accuracy and apply the machine learning methods to other plant species. [ABSTRACT FROM AUTHOR]

Globally, the amount of wetlands have being on the decline due to the fragile nature of these ecosystems and unplanned land consumption practices. This has created pressure on suitable land for cultivation in most developing countries where most of the growing food demand originates. Previous studies revealed that wetlands and agricultural landuse dominated the landscape of Makurdi. However, the trend is changing in recent times. Makurdi has undergone tremendous transformation in its landuse/landcover due to rapid urbanization since 1976 when it became the capital city of Benue State. To estimate the land cover change in Makurdi, Landsat ETM, ETM+ and OLI satellite data for 1996, 2006 and 2016, respectively were utilised. The study adapted the Kappa index for assessing accuracy of the land use/cover maps generated from the analysis to improve the accuracy of results. An accuracy level of 80 to 91% was achieved. The results reveal an overall significant increase in built-up area and other land uses at the expense of wetlands from 26.3% in 1996 to 18.1% in 2016. Further analysis includes the land consumption rate (LCR) and land absorption coefficient (LAC) which reveals the role of population expansion in the recorded levels of wetland losses recorded in this study. The study projects a further decline of wetland cover by 33.15 km2 (or by 22.57%) in 2026 if steps are not instituted to control the rate of decline. Suggestions are made to align with and incorporate into policy the strategic need to adopt the provisions of the SDGs at local levels if we intend to avert the massive failure recorded by the now rested MDGs. [ABSTRACT FROM AUTHOR]

In order to exploit efficiently very high resolution satellite multispectral data for precision agriculture applications, validated methodologies should be established which link the observed reflectance spectra with certain crop/plant/fruit biophysical and biochemical quality parameters. To this end, based on concurrent satellite and field campaigns during the veraison period, satellite and in-situ data were collected, along with several grape samples, at specific locations during the harvesting period. These data were collected for a period of three years in two viticultural areas in Northern Greece. After the required data pre-processing, canopy reflectance observations, through the combination of several vegetation indices were correlated with the quantitative results from the grape/must analysis of grape sampling. Results appear quite promising, indicating that certain key quality parameters (like brix levels, total phenolic content, brix to total acidity, anthocyanin levels) which describe the oenological potential, phenolic composition and chromatic characteristics can be efficiently estimated from the satellite data. [ABSTRACT FROM AUTHOR]

The development of UAV-based sensing systems for agronomic applications serves the improvement of crop management. The latter is in the focus of precision agriculture which intends to optimize yield, fertilizer input, and crop protection. Besides, in some cropping systems vehicle-based sensing devices are less suitable because fields cannot be entered from certain growing stages onwards. This is true for rice, maize, sorghum, and many more crops. Consequently, UAV-based sensing approaches fill a niche of very high resolution data acquisition on the field scale in space and time. While mounting RGB digital compact cameras to low-weight UAVs (< 5 kg) is well established, the miniaturization of sensors in the last years also enables hyperspectral data acquisition from those platforms. From both, RGB and hyperspectral data, vegetation indices (VIs) are computed to estimate crop growth parameters. In this contribut ion, we compare two different sensing approaches from a low-weight UAV platform (< 5 kg) for monitoring a nitrogen field experiment of winter wheat and a corresponding farmers' field in Western Germany. (i) A standard digital compact camera was flown to acquire RGB images which are used to compute the RGBVI and (ii) NDVI is computed from a newly modified version of the Yara N-Sensor. The latter is a well-established tractor-based hyperspectral sensor for crop management and is available on the market since a decade. It was modified for this study to fit the requirements of UAV-based data acquisition. Consequently, we focus on three objectives in this contribution: (1) to evaluate the potential of the uncalibrated RGBVI for monitoring nitrogen status in winter wheat, (2) investigate the UAV-based performance of the modified Yara N-Sensor, and (3) compare the results of the two different UAV-based sensing approaches for winter wheat. [ABSTRACT FROM AUTHOR]

The estimation of dendrometric parameters has become an important issue for the agricultural planning and management. Since the classical field measurements are time consuming and inefficient, Airborne Laser Scanning (ALS) data can be used for this purpose. Point clouds acquired for orchard areas allow to determine orchard structures and geometric parameters of individual trees. In this research we propose an automatic method that allows to determine geometric parameters of individual olive trees using ALS data. The method is based on the α-shape algorithm applied for normalized point clouds. The algorithm returns polygons representing crown shapes. For points located inside each polygon, we select the maximum height and the minimum height and then we estimate the tree height and the crown base height. We use the first two components of the Principal Component Analysis (PCA) as the estimators for crown diameters. The α-shape algorithm requires to define the radius parameter R. In this study we investigated how sensitive are the results to the radius size, by comparing the results obtained with various settings of the R with reference values of estimated parameters from field measurements. Our study area was the olive orchard located in the Castellon Province, Spain. We used a set of ALS data with an average density of 4 points m-2. We noticed, that there was a narrow range of the R parameter, from 0.48 m to 0.80 m, for which all trees were detected and for which we obtained a high correlation coefficient (>0.9) between estimated and measured values. We compared our estimates with field measurements. The RMSE of differences was 0.8 m for the tree height, 0.5 m for the crown base height, 0.6 m and 0.4 m for the longest and shorter crown diameter, respectively. The accuracy obtained with the method is thus sufficient for agricultural applications. [ABSTRACT FROM AUTHOR]

In this study, first results of retrieving plant heights of maize fields from multitemporal TanDEM-X images are shown. Three TanDEM-X dual polarization spotlight acquisitions were taken over a rural area in Germany in the growing season 2014. By interferometric processing, digital terrain models (DTM) were derived for each date with 5m resolution. From the data of the first acquisition (June 1st) taken before planting, a DTM of the bare ground is generated. The data of the following acquisition dates (July 15th, July 26th) are used to establish crop surface models (CSM). A CSM represents the crop surface of a whole field in a high resolution. By subtracting the DTM of the ground from each CSM, the actual plant height is calculated. Within these data sets 30 maize fields in the area of interest could be detected and verified by external land use data. Besides the spaceborne measurements, one of the maize fields was intensively investigated using terrestrial laser scanning (TLS), which was carried out at the same dates as the predicted TanDEM-X acquisitions. Visual inspection of the derived plant heights, and accordance of the individually processed polarisations over the maize fields, demonstrate the feasibility of the proposed method. Unfortunately, the infield variability of the intensively monitored field could not be successfully captured in the TanDEM-X derived plant heights and merely the general trend is visible. Nevertheless, the study shows the potential of the TanDEM-X constellation for maize height monitoring on field level. [ABSTRACT FROM AUTHOR]

Thanks to mainly ESA and USGS, a large bulk of free images of the Earth is readily available nowadays. One of the main goals of remote sensing is to label images according to a set of semantic categories, i.e. image classification. This is a very challenging issue since land cover of a specific class may present a large spatial and spectral variability and objects may appear at different scales and orientations. In this study, we report the results of benchmarking 9 machine learning algorithms tested for accuracy and speed in training and classification of land-cover classes in a Sentinel-2 dataset. The following machine learning methods (MLM) have been tested: linear discriminant analysis, k-nearest neighbour, random forests, support vector machines, multi layered perceptron, multi layered perceptron ensemble, ctree, boosting, logarithmic regression. The validation is carried out using a control dataset which consists of an independent classification in 11 land-cover classes of an area about 60 km2, obtained by manual visual interpretation of high resolution images (20 cm ground sampling distance) by experts. In this study five out of the eleven classes are used since the others have too few samples (pixels) for testing and validating subsets. The classes used are the following: (i) urban (ii) sowable areas (iii) water (iv) tree plantations (v) grasslands. Validation is carried out using three different approaches: (i) using pixels from the training dataset (train), (ii) using pixels from the training dataset and applying cross-validation with the k-fold method (kfold) and (iii) using all pixels from the control dataset. Five accuracy indices are calculated for the comparison between the values predicted with each model and control values over three sets of data: the training dataset (train), the whole control dataset (full) and with k-fold cross-validation (kfold) with ten folds. Results from validation of predictions of the whole dataset (full) show the random forests method with the highest values; kappa index ranging from 0.55 to 0.42 respectively with the most and least number pixels for training. The two neural networks (multi layered perceptron and its ensemble) and the support vector machines - with default radial basis function kernel - methods follow closely with comparable performance. [ABSTRACT FROM AUTHOR]

Geospatial data are available in raster and vector formats and some of them are available in open data form. The technique and tools to handle those data are also available in open source. Though it is free of charge, the knowledge to utilize those data is limited to non-educated in the specific field. The data and technology should be promoted to those levels to utilize in required fields with priceless in developing countries. Before utilize open data, which are required to verify with local knowledge to become usable information for the local people as priceless data resources. Developing country, which economic is based in agriculture, required more information about precise weather data and weather variation by the climate change impact for their socioeconomic development. This study found that rural to urban migration occurs in the developing countries such agriculture based country likes Myanmar when the agriculture economic are affected by unpredictable impact by the climate change. The knowledge sharing using open data resources to non-educated local people is one of the curable solutions for the agriculture economy development in the country. Moreover, the study will find ways to reduce the rural to urban migration. [ABSTRACT FROM AUTHOR]

The objective of this study is vulnerability and exposer intensity due to land use change in Olomouc, Czech Republic. Vulnerability assessment with exposer intensity to land use/cover change is an important step for enhancing the understanding and decision-making to reduce vulnerability. This study work includes quantification of Exposure Index (EI), Sensitivity Index (SI) and Adaptive Capacity Index (AI). EI is based on intensity of land use/cover change, SI and AI based on natural factors such as elevation, slope, vegetation and land use/cover. Vulnerability Index (VI) derived on the quantification of SI and AI and compared from 1991, 2001 and 2013. Comparing of EI and VI for last three decades, settlements have highest vulnerability index due to high socio-economic activities and water have lowest vulnerability index due to less human interferences. Agriculture has highest exposer index and second highest vulnerability, which show its high rate of exploitation and production. In the study areas, vulnerability tends to increase with the increase of exposure to land use change, but can peak off once the land use start to benefit socio-economically from development. Only in this way we can enhance the adaptive capacity of study area to use change of land. [ABSTRACT FROM AUTHOR]

This study investigates the scientific quality of the GEOV1 Leaf Area Index (LAI), Fraction of Absorbed Photosynthetically Active Radiation (FAPAR) and Fraction of Vegetation Cover (FCover) products based on PROBA-V observations. The procedure follows, as much as possible, the guidelines, protocols and metrics defined by the Land Product Validation (LPV) group of the Committee on Earth Observation Satellite (CEOS) for the validation of satellite-derived land products. This study is focused on the consistency of SPOT/VGT and PROBA-V GEOV1 products developed in the framework of the Copernicus Global Land Services, providing an early validation of PROBA-V GEOV1 products using data from November 2013 to May 2014, during the overlap period (November 2013-May 2014). The first natural year of PROBA-V GEOV1 products (2014) was considered for the rest of the quality assessment including comparisons with MODIS C5. Several criteria of performance were evaluated including product completeness, spatial consistency, temporal consistency, intra-annual precision and accuracy. Firstly, and inter-comparison with both spatial and temporal consistency were evaluated with reference satellite products (SPOT/VGT GEOV1 and MODIS C5) are presented over a network of sites (BELMANIP2.1). Secondly, the accuracy of PROBA-V GEOV1 products was evaluated against a number of concomitant agricultural sites is presented. The ground data was collected and up-scaled using high resolution imagery in the context of the FP7 ImagineS project in support of the evolution of Copernicus Land Service. Our results demonstrate that GEOV1 PROBA-V products were found spatially and temporally consistent with similar products (SPOT/VGT, MODISC5), and good agreement with limited ground truth data with an accuracy (RMSE) of 0.52 for LAI, 0.11 for FAPAR and 0.14 for FCover, showing a slight bias for FCover for higher values. [ABSTRACT FROM AUTHOR]

One of the most popular approaches to process high-density proximal soil sensing data is to aggregate similar measurements representing unique field conditions. An innovative constraint-based spatial clustering algorithm has been developed. The algorithm seeks to minimize the mean squared error during the interactive grouping of spatially adjacent measurements similar to each other and different from the other parts of the field. After successful implementation of a one soil property scenario, this research was to accommodate multiple layers of soil properties representing the same area under investigation. Six agricultural fields across Nebraska, USA, were chosen to illustrate the algorithm performance. The three layers considered were field elevation and apparent soil electrical conductivity representing both deep and shallow layers of the soil profile. The algorithm was implemented in MATLAB, R2013b. Prior to the process of interactive grouping, geographic coordinates were projected and erroneous data were filtered out. Additional data pre-processing included bringing each data layer to a 20x20 m raster to facilitate multi-layer computations. An interactive grouping starts with a new "nest" search to initiate the first group of measurements that are most different from the rest of the field. This group is grown using a neighbourhood search approach and once growing the group fails to reduce the overall mean squared error, the algorithm seeks to locate a new "nest", which will grow into another group. This process continues until there is no benefit from separating out an additional part of the field. Results of the six-field trial showed that each case generated a reasonable number of groups which corresponded to agronomic knowledge of the fields. The unique feature of this approach is spatial continuity of each group and capability to process multiple data layers. Further development will involve comparison with a more traditional k-means clustering approach and agronomic model calibration using a targeted soil sampling. [ABSTRACT FROM AUTHOR]

Over the last decades, the role of remote sensing gained in importance for monitoring applications in precision agriculture. A key factor for assessing the development of crops during the growing period is the actual biomass. As non-destructive methods of directly measuring biomass do not exist, parameters like plant height are considered as estimators. In this contribution, first results of multitemporal surveys on a maize field with a terrestrial laser scanner are shown. The achieved point clouds are interpolated to generate Crop Surface Models (CSM) that represent the top canopy. These CSMs are used for visualizing the spatial distribution of plant height differences within the field and calculating plant height above ground with a high resolution of 1 cm. In addition, manual measurements of plant height were carried out corresponding to each TLS campaign to verify the results. The high coefficient of determination (R² = 0.93) between both measurement methods shows the applicability of the presented approach. The established regression model between CSM-derived plant height and destructively measured biomass shows a varying performance depending on the considered time frame during the growing period. This study shows that TLS is a suitable and promising method for measuring plant height of maize. Moreover, it shows the potential of plant height as a non-destructive estimator for biomass in the early growing period. However, challenges are the non-linear development of plant height and biomass over the whole growing period. [ABSTRACT FROM AUTHOR]

Crop-Surface-Models (CSMs) are a useful tool for monitoring in-field crop growth variability, thus enabling precision agriculture which is necessary for achieving higher agricultural yields. This contribution provides a first assessment on the suitability of using consumer-grade smart cameras as sensors for the stereoscopic creation of crop-surface models using oblique imagery acquired from ground-based positions. An application that automates image acquisition and transmission was developed. Automated image acquisition took place throughout the growing period of barley in 2013. For three dates where both automated image acquisition and manual measurements of plant height were available, CSMs were generated using a combination of AgiSoft PhotoScan and Esri ArcGIS. The coefficient of determination R² between the average of the manually measured plant heights per plots and the average height of the developed crop surface models was 0.61 (n = 24). The overall correlation between the manually measured heights and the CSM-derived heights is 0.78. The average per plot of the manually measured plant heights in the timeframe covered by the generated CSMs range from 19 to 95 cm, while the average plant height per plot of the generated CSMs range from 2.1 to 69 cm. These first results show that the presented approach is feasible. [ABSTRACT FROM AUTHOR]