Andrea Borgo

Reliable crop mapping is essential for understanding agricultural practices, optimizing resource use, and analyzing rural dynamics, while also supporting modelling and sustainable agriculture planning. However, obtaining 10 m crop distribution maps remains challenging in Mediterranean regions, where data availability is often limited and landscapes are fragmented. The main European land use dataset, Corine Land Cover (CLC), lacks both the crop specificity required for accurate crop differentiation and the temporal frequency needed for timely monitoring. This study addresses these limitations by implementing the IOTA² automated chain in Sardinia (Italy), to create a large-scale crop map specifically targeting Mediterranean crops. The methodology leverages open-source satellite imagery with supervised machine learning, using the 2018 Land Parcel Identification System (LPIS), CLC, and Urban Atlas dataset for training. We compared two nomenclatures, detailed (32 classes) versus simplified (25 classes), testing each across three training sample sizes (10%, 50%, and 100%). Results indicate that the simplified nomenclature (N25) provided more robust performances, achieving an overall accuracy (OA) of 0.77 with full sampling, compared to 0.61 for the detailed version. These OA values refer to the subset of reference polygons held out from the reference data for independent pixel-level validation. Moreover, a final map was produced using the entire reference dataset for training and evaluated through zonal area agreement. Mapping showed high performance for specific crops like rice, citrus, and grapevine, while classes such as cereals and fruit trees presented classification challenges due to high fragmentation of the landscape and irregular crop-distribution patterns. Despite these challenges, this work delivers a 10 m spatial resolution reproducible framework that enhances thematic details of current European datasets. By running as a single automated processing chain rather than a sequence of manually executed steps, it offers a scalable solution for rapid, annual crop monitoring in complex, data-scarce Mediterranean environments.

Efficient water management is critical in modern agriculture due to unsustainable depletion of water resources, intensified by climate change. Digital technologies such as IoT offer opportunities to optimize water use through precise, real-time assessment of water requirements. This study presents ACQUAOUNT-Farm, a real-time platform designed to assist farmers in irrigation planning across Mediterranean environments. The tool integrates on-site IoT sensors (soil moisture, water flow, weather) with a physically based model following the FAO-56 dual crop coefficient approach, embedded within a user-friendly interface. The platform requires minimal input data, providing soil moisture monitoring and scheduling capabilities suitable for non-expert users. ACQUAOUNT-Farm updates daily, reconstructing hourly soil moisture and irrigation needs up to one week ahead and generating an irrigation calendar based on crop-specific water stress thresholds. ACQUAOUNT-Farm was tested on four farms in southern Tunisia for citrus and potato crops (2024-2025). Simulated and observed soil moisture showed good agreement for three out of four farms (R² ≈ 0.65, RMSE ≈ 0.022 m³ m⁻³, MAE ≈ 0.016 m³ m⁻³), with errors below sensor accuracy (0.03 m³ m⁻³) up to two days in all farms, confirming the model's forecasting ability. Compared to farmers' practices, ACQUAOUNT-Farm indicated water savings of 63–65% for one citrus field and 80–84% for autumn potato, while spring potato showed 17–33% savings. In one citrus field, the model confirmed the farmer's deficit irrigation strategy. These results suggest that ACQUAOUNT-Farm has the potential to support farmers in Mediterranean regions in reducing water withdrawals.

The impact of climate change on droughts is typically attributed to rising temperatures and altered precipitation patterns. Yet, most drought projections overlook a major climate-induced mechanism: the effect of elevated CO₂ on plant physiology, leading to a significant potential overestimation of droughts magnitudes and impacts. In fact, elevated CO₂ enhances biomass production and reduces stomatal conductance, thereby increasing water-use efficiency . Our systematic review reveals that nearly 90% of evapotranspiration-based drought projections omit CO₂-driven vegetation feedback, and only 10% acknowledge this limitation. Neglecting vegetation response to CO2 can overestimate future drought-affected areas by up to 17.4 ± 10.6% under high-emission scenarios (CO₂ > 900 ppm), and in some regions even reverse the projected direction of change. This widespread oversight can hamper the robustness of global drought projections. Accounting for vegetation–CO₂ interactions is therefore crucial to avoid systematic bias and produce reliable predictions of water availability in a warming world.

Efficient water management is increasingly more critical in modern agriculture due to unsustainable depletion of water resources, intensified by climate change and growing competition among sectors. Digital technologies such as the Internet of Things (IoT) offer new opportunities to optimize water use by enabling precise, real-time assessment of water requirements to withhold sustained crop productivity. This study presents ACQUAOUNT-Farm, a real-time platform, designed to assist farmers in daily irrigation planning. The tool integrates on-site IoT sensors (soil moisture, water flow and weather) with a user-friendly interface to monitor soil moisture dynamics and provide flexible irrigation scheduling. ACQUAOUNT-Farm requires a minimal set of easily accessible inputs, making it suitable for non-expert users. The model updates daily, it reconstructs hourly soil moisture and irrigation needs up to one week ahead and it generates an irrigation calendar based on crop-specific water stress thresholds, offering recommendations for an early, late, and limited irrigation application. The model was tested in four farms in southern Tunisia for citrus and potato crops during two growing seasons (2024-2025). Comparison between simulated and observed soil moisture showed good agreement (R² > 0.76), confirming the model’s ability to forecast soil moisture dynamics. When compared with farmers’ irrigation practices, ACQUAOUNT-Farm indicated potential water savings of around 60% for one citrus field and 70–80% for autumn potato, while spring potato showed limited savings due to high seasonal water demand. In one citrus field, the model recommended 40% more water to reach optimal productivity, reflecting the farmer’s deficit irrigation strategy, already implemented in the field. Overall, ACQUAOUNT-Farm demonstrates strong potential to enhance irrigation efficiency and reduce water withdrawals.