This article presents a novel system that produces multiyear high-resolution irrigation water demand maps for agricultural areas, enabling a new level of detail for irrigation support for farmers and ...agricultural stakeholders. The system is based on a scalable distributed deep learning (DL) model trained on dense time series of Sentinel-2 images and a large training set for the first year of observation and fine tuned on new labeled data for the consecutive years. The trained models are used to generate multiyear crop type maps, which are assimilated together with the Sentinel-2 dense time series and the meteorological data into a physically based agrohydrological model to derive the irrigation water demand for different crops. To process the required large volume of multiyear Copernicus Sentinel-2 data, the software architecture of the proposed system has been built on the integration of the Food Security thematic exploitation platform (TEP) and the data-intensive artificial intelligence Hopsworks platform. While the Food Security TEP provides easy access to Sentinel-2 data and the possibility of developing processing algorithms directly in the cloud, the Hopsworks platform has been used to train DL algorithms in a distributed manner. The experimental analysis was carried out in the upper part of the Danube Basin for the years 2018, 2019, and 2020 considering 37 Sentinel-2 tiles acquired in Austria, Moravia, Hungary, Slovakia, and Germany.
The annual certification of organic agriculture products includes an in situ inspection of the fields declared organic. This inspection is more difficult, time-consuming, and costly for large farms ...or in production regions located in remote areas. The global objective of this research is to assess how spatial remote sensing may support the organic crop certification process by developing a method that would enable certification bodies to target for priority in situ control crop fields declared as organic but that would show on satellite imagery an appearance closer to conventional fields. For this purpose, the ability of multispectral satellite images to discriminate between organic and conventional maize fields was assessed through the use of a set of four satellite images of different spatial and spectral resolutions acquired at different crop growth stages over a large number of maize fields (32) that are part of an operational farm in Germany. In support of this main objective, a set of in situ measurements (leaf hyperspectral reflectance, chlorophyll, and nitrogen content and dry matter percentage, crop canopy cover, height, wet biomass and dry matter percentage, soil chemical composition) was conducted to characterize the nature of the biochemical and biophysical differences between organic and conventional maize fields. The results of this research showed that highly significant biochemical and biophysical differences between a large number of organic and conventional maize fields may exist at identified crop growth stages and that these differences may be sufficiently pronounced to enable the complete discrimination between crop management modes using satellite images issued from quite common multispectral satellite sensors through the use of spectral or spatial heterogeneity indices. These results are very encouraging and suggest, for the first time, that satellite images could effectively support the organic maize certification process.
This paper presents a novel system that produces multi-year high-resolution irrigation water demand maps for agricultural areas enabling a new level of detail for irrigation support for farmers and ...agricultural stakeholders. The system is based on a scalable distributed Deep Learning (DL) model trained on dense time series of Sentinel-2 images and a large training set for the first year of observation, and fine-tuned on new labeled data for the consecutive years. The trained models are used to generate multi-year crop type maps, which are assimilated together with the Sentinel-2 dense time series and the meteorological data into a physically based agro-hydrological model to derive the irrigation water demand for different crops. To process the required large volume of multi-year Copernicus Sentinel-2 data, the software architecture of the proposed system has been built on the integration of the Food Security TEP and the data-intensive arpngicial intelligence Hopsworks platform. While the Food Security TEP provides easy access to Sentinel- 2 data and the possibility of developing processing algorithms directly in the cloud, the Hopsworks platform has been used to train DL algorithms in a distributed manner. The experimental analysis was carried out in the upper part of the Danube Basin for the years 2018, 2019 and 2020 considering 37 Sentinel-2 tiles acquired in Austria, Moravia, Hungary, Slovakia and Germany.
Applications of hyperspectral remote sensing data to derive relevant properties for precision agriculture are described. Green leaf area index, fraction of senescent material and grain yield are ...retrieved from the hyperspectral data. Two sensors were used to obtain these data; the airborne visible/infrared imaging spectrometer AVIS and the space-borne compact high-resolution imaging spectrometer CHRIS; they show the applicability of the methods to different spatial scales. In addition, the bi-directional observation capability of the CHRIS sensor is used to derive information about the average leaf angle of the canopies which are used to link canopy structure with phenological development. Derivation of the canopy properties, green leaf area index and fraction of senescent material was done with the radiative transfer model, SLC (soil-leaf-canopy). The results were used as input into the crop growth model PROMET-V to calculate grain yield. Two years of data from the German research project preagro are presented.
The spectral information contained in hyperspectral data allows for a more detailed crop and soil parameter retrieval, in turn making possible to derive precise information about plant health ...(nutrient deficiencies, water stress, crop diseases) but also about soil status (from soil moisture to humus content). Thus, smart farming, that is farming practice that wants to account for the whole ecosystem on the field and react precisely to any challenges, can be supported by hyperspectral data with exactly the spatial information it needs.
For a sustainable and efficient land management, spatially distributed and up-to-date information on the land surface is of central importance. A continuous flow of land management information is the ...basis to improve decisions on use, cultivation intensity and allocation of resources (e.g. water for irrigation). Remote sensing is in a unique position to contribute to this task as it is globally available and provides specific information about current crop status. The M 4 Land concept is designed to derive information products for a sustainable management of the land surface. In this paper, the methodology and the results for the autonomous development of three products, i.e. land use, crop cycle and intensity of agricultural use, is presented for two test sites and for several years. In the M 4 Land system, a crop growth model (PROMET) and a reflectance model (SLC) are coupled in order to provide these information products by analyzing multi-temporal and multi-sensoral satellite images.
A method to derive products for a sustainable management of the land surface is developed in the frame of the M 4 Land project ("Model based, Multi-temporal, Multi-scale and Multi-sensoral retrieval ...of continuous land management information"). The system relies on a model-supervised dynamic classification of land cover from multi-temporal satellite data that works automatically without the need for training data or manual data processing. This approach is tested for the first time in a mesoscale setting (300m resolution). The performed model-supervised land cover classification of ENVISAT MERIS data at a test site in Southern Germany in 2010 is promising with an overall accuracy of 84.7%. After the consolidation of the method on this scale further land management products can be developed that are based on the underlying land surface model data.