Abstract:Crop growth models simulate the relationship between plants and the environment to predict the expected yield for applications such as crop management and agronomic decision making, as well as to study the potential impacts of climate change on food security. A major limitation of crop growth models is the lack of spatial information on the actual conditions of each field or region. Remote sensing can provide the missing spatial information required by crop models for improved yield prediction. This paper reviews the most recent information about remote sensing data and their contribution to crop growth models. It reviews the main types, applications, limitations and advantages of remote sensing data and crop models. It examines the main methods by which remote sensing data and crop growth models can be combined. As the spatial resolution of most remote sensing data varies from sub-meter to 1 km, the issue of selecting the appropriate scale is examined in conjunction with their temporal resolution. The expected future trends are discussed, considering the new and planned remote sensing platforms, emergent applications of crop models and their expected improvement to incorporate automatically the increasingly available remotely sensed products.

Remote sensing techniques are routinely used in plant species discrimination and of weed mapping. In the presented work, successful Silybum marianum detection and mapping using multilayer neural networks is demonstrated. A multispectral camera (green-red-near infrared) attached on a fixed wing unmanned aerial vehicle (UAV) was utilized for the acquisition of high-resolution images (0.1 m resolution). The Multilayer Perceptron with Automatic Relevance Determination (MLP-ARD) was used to identify the S. marianum among other vegetation, mostly Avena sterilis L. The three spectral bands of Red, Green, Near Infrared (NIR) and the texture layer resulting from local variance were used as input. The S. marianum identification rates using MLP-ARD reached an accuracy of 99.54%. Τhe study had an one year duration, meaning that the results are specific, although the accuracy shows the interesting potential of S. marianum mapping with MLP-ARD on multispectral UAV imagery.

Earth Observation (EO) data are increasingly being used to monitor vegetation and detect plant growth anomalies due to water stress, drought, or pests, as well as to monitor water availability, weather conditions, disaster risks, land-use/land-cover changes and to evaluate soil degradation. Satellite data are provided regularly by worldwide organizations, covering a wide variety of spatial, temporal and spectral characteristics. In addition, climate and crop growth models provide early estimates of the expected weather patterns and yield, which can be improved by fusion with EO data. The project "AfriCultuReS" is capitalizing on the above to contribute towards an integrated agricultural monitoring and early warning system for Africa, supporting decision making in the field of food security. The aim of this paper is to present the design of EO services within the project, and how they will support food security in Africa. The designed services cover the users' requirements related to climate, drought, land, livestock, crops, water, and weather. For each category of services, results from one case study are presented. The services will be distributed to the stakeholders and are expected to provide a continuous monitoring framework for early and accurate assessment of factors affecting food security in Africa.

The Leaf Area Index (LAI) is an important indicator of vegetation development which can be used as an input parameter in hydrological and biochemical models (e.g. crop models for yield prediction and forecast) and is, thus, relevant information to monitor food production and to feed an early warning system for famine crisis. Satellite LAI data is available on a regular basis (high temporal resolution) with maps at regional or global scales (low spatial resolution). This study aimed at enhancing the spatial resolution of the MODIS LAI product to bring it to the Landsat resolution. The proposed method was applied in four sites with different climate and vegetation conditions. Regression analysis between MODIS EVI (Enhanced Vegetation Index) and LAI data was applied across time and the estimated regression equations were input in a downscaling model using Landsat EVI images and land cover maps. Comparison between the downscaled LAI values and LAI field measurements showed high correlation, with correlation coefficient values ranging from moderate (0.5 -0.7 in two cases) to high (0.7 -0.96 in five cases). The results show that it is possible to use this methodology to reliably estimate LAI at a 30m spatial resolution across various climates and ecosystems, thus supporting a food security early warning system.

Smallholder farmers produce about 70% of Africa's food supply. These farmers are vulnerable to a number of risks, mainly climate related, which have a tremendous impact on food security and thus poverty. Information about crop yields, vegetation conditions and weather, among others, are essential to policy makers to enhance food security. Earth observation data, analytics and modeling from various sources, at a variety of spatial and temporal scales could be used to support policy and decision making in the field of food security. This paper describes crops, water and drought services that are being developed in the AfriCultuReS project. Preliminary results are presented, which reflect the uneven distribution of precipitation, water bodies, and vegetation conditions throughout Africa.