The present study focuses on the use of Convolutional Neural Networks (CNN or ConvNet) to classify a multi-seasonal dataset of Sentinel-2 images to discriminate four grassland habitats in the “Murgia Alta” protected site. To this end, we compared two approaches differing only by the first layer machinery, which, in one case, is instantiated as a fully-connected layer and, in the other case, results in a ConvNet equipped with kernels covering the whole input (wide-kernel ConvNet). A patchwise approach, tessellating training reference data in square patches, was adopted. Besides assessing the effectiveness of ConvNets with patched multispectral data, we analyzed how the information needed for classification spreads to patterns over convex sets of pixels. Our results show that: (a) with an F1-score of around 97% (5 × 5 patch size), ConvNets provides an excellent tool for patch-based pattern recognition with multispectral input data without requiring special feature extraction; (b) the information spreads over the limit of a single pixel: the performance of the network increases until 5 × 5 patch sizes are used and then ConvNet performance starts decreasing.

ALtimetry for BIOMass (ALBIOM) is a Permanent Open Call Project funded by the European Space Agency (ESA) to explore the possibility of forest biomass retrieval by using Copernicus Sentinel-3 (S-3) Synthetic aperture Radar ALtimeter (SRAL) in low- and high-resolution mode at Ku- and C-bands. It represents an original work in the research of new techniques for vegetation observation using altimetry data. Because of the complexity of the land surfaces, no algorithm has been developed for a specific retracking of the altimetric land waveform. This calls for the development of a model able to reproduce the acquisition system and the target scattering phenomena to simulate the interaction of the radar pulse with the land. In this first work, we present the electromagnetic simulator of S-3 SRAL altimeter measurements over bare soil scenarios realized through a modification of the Soil and Vegetation Reflection Simulator (SAVERS) simulator developed by the team for Global Navigation Satellite System Reflectometry (GNSS-R) over land. The impact of topography has also been taken into account. We demonstrate that SAVERS for S-3 SRAL proved its capability to reproduce altimeter waveforms’ main attributes for both flat and topography scenarios.

The Sahel is one of the regions with the highest rates of food insecurity in the world. Understanding the driving factors of agricultural productivity is, therefore, essential for increasing crop yields whilst adapting to a future that will be increasingly dominated by climate change. This paper shows how meteo-climatic variables, combined with fertilizers’ application rates, have affected the productivity of two important crops in the Sahel region, i.e. maize and millet, over the last three decades. To this end, we have applied a specifically designed neural network tool (optimised for analysis of small datasets), endowed with feed-forward networks and backpropagation training rules and characterised by generalised leave-one-out training and multiple runs of neural network models in an ensemble strategy. This tool allowed us to identify and quantify the impacts of single drivers and their linear and nonlinear role. The variables analysed included temperature, precipitation, atmospheric CO₂ concentration, chemical and organic fertilizer input. They explained most of the variance in the crop data (R² = 0.594 for maize and R² = 0.789 for millet). Our analysis further allowed us to identify critical threshold effects affecting yields in the region, such as the number of hours with temperature higher than 30 °C during the growing season. The results identified heat waves and fertilizer application rates playing a critical role in affecting maize and millet yields in this region, while the role of increasing CO₂ was less important. Our findings help identify the modalities of ongoing and future climate change impacts on maize and millet production in the Sahel.

Forests play a crucial role in the climate change mitigation by acting as sinks for carbon and, consequently, reducing the CO2 concentration in the atmosphere and slowing global warming. For this reason, above ground biomass (AGB) estimation is essential for effectively monitoring forest health around the globe. Although remote sensing-based forest AGB quantification can be pursued in different ways, in this work, we discuss a new technique for vegetation observation through the use of altimetry data that have been introduced by the ESA-funded ALtimetry for BIOMass (ALBIOM) project. ALBIOM investigates the possibility of retrieving forest biomass through Copernicus Sentinel-3 Synthetic Aperture Radar Altimeter (SRAL) measurements at the Ku- and C-bands in low- and high-resolution modes. To reach this goal, a simulator able to reproduce the altimeter acquisition system and the scattering phenomena that occur in the interaction of the radar altimeter pulse with vegetated surfaces has been developed. The Tor Vergata Vegetation Scattering Model (TOVSM) developed at Tor Vergata University has been exploited to simulate the contribution from the vegetation volume via the modeling of the backscattering of forest canopy through a discrete scatterer representation. A modification of the Soil And Vegetation Reflection Simulator (SAVERS) developed by the team for Global Navigation Satellite System Reflectometry over land has also been taken into account to simulate the soil contribution.