Spatiotemporal mapping of protected agriculture and its impacts on water consumption

Berry production ranks as the second crop with the highest export value in Mexico, with the Zamora Valley in the western part of Michoacan state being notable for its production. This region mainly utilizes greenhouses, macrotunnels, and shade houses for cultivation. However, there is a lack of specific data regarding the spatiotemporal distribution and water consumption associated with these crops. To address this gap, Sentinel-2 images from three years were analyzed to implement a land use and land cover classification using the Random Forest algorithm. This analysis provided insight into the spatial distribution and temporal variability of protected crops. The achieved overall accuracy exceeded 90%, with an F1-score for the protected crops class also above 90%. The results show strong spatiotemporal variability in the area designated for protected crops, with 83% of this area changing partially or entirely to uncultivated plots or seasonal crops, related to local production models. Additionally, two critical zones experiencing substantial increases in hectares dedicated to protected agriculture were identified. These zones are located in the conurbations of Jacona and Zamora cities, and the southern region of Atacheo town, showing concentrations of up to 18 ha with an estimated minimum water demand between 80,000 and 186,900 m3. Ultimately, this research provides a first approach to understanding the spatial distribution, water consumption, and production models of protected agriculture in regions with limited information. This data is crucial for informing and improving water distribution plans and monitoring agricultural water use.