Water scarcity is a prominent consequence of global climate change, presenting a significant challenge to the livelihoods of wide parts of the world, particularly in arid and semi-arid regions. This study focuses on Erbil Province in Iraq, where the dual effects of climate change and human activity have significantly depleted water resources in the past two decades. To address this challenge, rainwater harvesting (RWH) is explored as a viable solution. The purpose of this study is to make a suitability zone map that divides the study area into several classes based on the features of each area and its ability to collect rainwater. The map will then be used to find the best place to build different RWH structures. Seven different layers are used to make the RWH suitability zone map: rainfall, runoff, land use/cover (LU/LC), soil texture, slope, drainage density, and the Topographic Wetness Index (TWI). Each layer was assigned specific weights through the Analytical Hierarchy Process (AHP), considering its relevance to RWH. Results revealed four suitability classes: very highly suitable 1583.25 km² (10.67%), highly suitable 4968.55 km² (33.49%), moderately suitable 5295.65 km² (35.69%), and lowly suitable 2989.66 km² (20.15%). Notably, the suitability map highlights the northern and central regions as particularly suitable for RWH. Furthermore, the study suggested three suitable locations for constructing medium dams, six for check dams, and twenty-seven for farm ponds, according to the requirements of each type. These findings provide valuable insights for the strategic planning and effective management of water resources in the study area, offering potential solutions to the pressing challenges of water scarcity.

Yield prediction in wheat cultivated under semi-arid climatic conditions is gaining increasing importance for sustainable production strategies and decision support systems. In this study, a time-series-based modeling approach was implemented using sensor-based data (SPAD, NSPAD, NDVI, INSEY, and plant height measurements collected at four different Zadoks growth stages (ZD24, ZD30, ZD31, and ZD32). Five different machine learning algorithms (Random Forest, Gradient Boosting, AdaBoost, LightGBM, and XGBoost) were tested individually for each stage, and the model performances were evaluated using statistical metrics such as R²%, RMSE t/ha, and MAE t/ha. Modeling results revealed that the ZD31 stage (first node detectable) was identified as the most successful phase for prediction accuracy, with the XGBoost model achieving the highest R²% score (81.0). In the same model, RMSE and MAE values were calculated as 0.49 and 0.37, respectively. The LightGBM model also showed remarkable performance during the ZD30 stage, achieving an R²% of 78.0, an RMSE of 0.52, and an MAE of 0.40. The SHAP (SHapley Additive exPlanations) method used to interpret feature importance revealed that the NDVI and INSEY indices contributed the most significant values to prediction accuracy for yield. This study demonstrates that phenology-sensitive yield prediction approaches offer high potential for sensor-based digital applications. Furthermore, the integration of timing, model selection, and explainability provided valuable insights for the development of advanced decision support systems.