Seasonal snow is a critical water resource in Northern Kazakhstan, where spring snowmelt dominates surface runoff and agricultural water supply. However, traditional rainwater harvesting frameworks often neglect snow water equivalent (SWE), limiting their applicability in cold, snow-dominated steppe environments. This study develops an integrated remote sensing and GIS-based approach to identify potential sites for spring runoff harvesting. Using Sentinel-2 imagery, snow cover fraction (SCF) was derived and combined with a digital elevation model (DEM) to estimate snow depth through a quadratic regression model, validated against in situ data from 23 meteorological stations. Snow water equivalent was then calculated by incorporating field-measured snow density. Alongside SWE, six additional parameters—slope, drainage density, land use/land cover (LULC), and soil texture (sand, silt, clay)—were integrated within an Analytical Hierarchy Process (AHP) multi-criteria decision analysis. Results show that SWE, drainage density, and LULC collectively contributed 75% of the weight in site suitability, underscoring their dominant role in snowmelt-driven hydrology. The final suitability map indicates that 28.03% of the region falls into the “Very High” class, concentrated in central and northwestern districts. Developing just 30% of these potential zones could yield approximately 4.2 × 10⁸ m³ of usable meltwater, supporting up to 105,000 ha under full irrigation or 280,000 ha under deficit irrigation. The study demonstrates that integrating high-resolution SWE with MCDA provides a scalable framework for enhancing agricultural resilience, mitigating floods, and strengthening water security in cold, semi-arid landscapes.

Mass locust invasions pose a significant threat to agricultural productivity in Kazakhstan. Locust attacks pose a serious threat to Kazakhstan's agricultural productivity. In order to determine the fundamental predictors of the number of locusts in the Central, Eastern and northern parts of Kazakhstan for each agro-climatic zone, on the basis of machine learning algorithms, perennial historical data on the dynamics of the number of studied pests in the period 2003-2024, depending on the influence of weather, climatic and edaphic (soil) factors, were processed and analyzed. Agroclimatic zones with different characteristics were considered. Such a wide coverage of the regions made it possible to take into account thediversity of conditions and identify the main factors (main predictors) that affect the number of phytophages studied. In this study, using field data from 2003 to 2024 and regional climate variables from ERA5 obtained via Google Earth Engine, we applied machine learning models to forecast the population dynamics of migratory locusts.We employed CatBoost, SARIMAX, and LSTM algorithms, comparing their performance on the input datasets. The LSTM model achieved the highest prediction accuracy (MAE = 0.36, RMSE = 0.59), effectively capturing temporal dependencies. Our results emphasize the importance of incorporating climatic factors such as soil moisture, temperature, and precipitation in forecasting models. These findings contribute to the development of targeted pest control strategies tailored to specific agroclimatic zones and enhance forecasting and monitoring methods based on GIS and computational modeling

This article presents an approach to assessing land suitability for irrigated agriculture based on the Multi-Criteria Decision Analysis (MCDA) method using weighted summation. The aim of the study is to integrate various factors affecting the potential of land for irrigation, taking into account their relative importance. The study is focused on the development and testing of a methodology for evaluating the degree of land suitability for irrigated agriculture in the North Kazakhstan Region of the Republic of Kazakhstan. Ten key criteria were identified and quantitatively assessed, including soil, geological parameters, land use, and others. The Analytic Hierarchy Process (AHP) method was used to determine the weights of the criteria, which made it possible to structure complex decisions based on pairwise comparisons of criteria. The calculation results, presented in the form of a spatial differentiation map, showed zones with different degrees of suitability for irrigated agriculture. The analysis showed that a high degree of suitability is mainly observed in the northwestern part of the region near lakes and along the Ishim River, whereas lands with low suitability prevail in the southern and southeastern parts. The developed methodology makes it possible not only to determine the current potential of land resources but also to take into account factors affecting their sustainability in the long term. This provides a basis for informed decision-making in the field of sustainable agricultural development and planning, as well as for identifying promising areas for the development of irrigated systems.