Second-crop corn is an important component of Brazilian grain production and is highly exposed to climatic variability because crop development occurs during the transition from the rainy to the drier season. This study assessed the performance of machine learning algorithms for estimating second-crop corn yield within the 2012–2023 historical data domain in Mato Grosso do Sul, Brazil. Municipal yield data from 22 municipalities and daily climatic data covering the period from 2012 to 2023 were analyzed. Yield data were obtained from Aprosoja/MS, whereas climatic variables, including solar radiation, air temperature, evapotranspiration, relative humidity, wind speed, and precipitation, were obtained from NASA/POWER. Pearson correlation analysis was used as an initial screening procedure to identify climatic variables associated with yield variability. Multiple linear regression (MLR), a multilayer perceptron (MLP), a support vector machine (SVM), Random Forest (RF), XGBoost, and a gradient boosting regressor (GBR) were evaluated. Under the observation-level random partition adopted in this study, RF and XGBoost showed the highest performance in the randomly held-out testing subset, both reaching R2 values of approximately 0.80. However, XGBoost exhibited near-perfect calibration performance followed by a substantial decrease during testing (MAPE = 14.05%; R2 = 0.80), indicating overfitting. Random Forest achieved similar testing performance with a smaller calibration-to-testing gap. Therefore, under the specific random partition used in this study, RF was considered the preferred model. In contrast, GBR failed to provide reliable predictive performance under the present dataset and configuration, with a testing MAPE of 547.78%, and was therefore considered too unreliable for interpretation in this study. Importantly, because the partition did not preserve temporal or spatial independence, these results represent generalization within the 2012–2023 historical data domain and should not be interpreted as evidence of future-year or spatially independent predictive performance. Because the dataset was partitioned randomly at the observation level without preserving temporal independence, the reported performance represents generalization within the 2012–2023 historical data domain and should not be interpreted as future-year forecasting performance.
Winter precipitation in Northeastern Asia has important implications for regional climate and weather hazards, yet its month-to-month evolution under global warming remains poorly understood. Using observations and the Policy Decision-making for Future climate change (d4PDF) large-ensemble simulations, this study investigates winter precipitation from November to March (NDJFM) and its projected changes under +2 K and +4 K global warming. Observations show a broadly U-shaped month-to-month evolution, with less precipitation in midwinter than at the beginning and end of winter. d4PDF generally reproduces the observed spatial pattern and month-to-month evolution, despite some regional biases. Winter precipitation is projected to increase across Northeastern Asia, with larger relative increases over the dry continental regions. Warming also reorganizes the monthly distribution of precipitation: the U-shaped evolution generally weakens, while the direction of subseasonal shifts varies regionally. Moisture-budget analysis indicates that submonthly moisture transport plays an important role in wintertime moisture convergence and its projected changes. Over the continental regions, enhanced submonthly moisture convergence offsets changes associated with the monthly mean flow, while thermodynamic effects dominate changes in the monthly component.
Sustainable expansion of irrigated agriculture requires the identification of areas with favorable biophysical conditions while also considering water-resource and infrastructure constraints. This study assessed the biophysical land suitability for potential irrigation development within the Ertis Water Management Basin (WMB), Kazakhstan, using an integrated remote sensing, geographic information system (GIS), and Analytic Hierarchy Process (AHP) framework. Four criteria—slope, normalized difference vegetation index (NDVI), land use/land cover (LULC), and soil texture—were standardized into five suitability classes and integrated using an AHP-based weighted overlay. The derived weights were 0.51 for slope, 0.26 for NDVI, 0.14 for LULC, and 0.09 for soil texture, with a consistency ratio of approximately 1%. The resulting assessment classified approximately 10% of the basin as highly suitable (S1), 43% as suitable (S2), 18% as moderately suitable (S3), 2% as marginally suitable (S4), and 27% as not suitable (NS), indicating that approximately 53% of the basin falls within the two highest suitability classes. Regional analysis showed that substantial shares of suitable land are concentrated in Pavlodar and Abay Regions, while suitable areas were identified across a wide range of distances from the river network. These findings indicate considerable biophysical potential for irrigation development across the Ertis WMB, with suitable areas occurring both near and farther from the river network. The resulting suitability map provides a spatial basis for identifying areas where more detailed assessments of water availability, irrigation infrastructure, and development feasibility can subsequently be undertaken.
This study investigates the effectiveness of informal and formal education channels in driving pro-environmental behavioral changes and situational learning outcomes among visitors in open-air educational settings. Using Skiathos Island (Greece) and its protected Natura 2000 wetland as an ambient learning laboratory, the research examines how ecological knowledge transfer translates into internalized ethical conduct. Utilizing a structural equation modelling (SEM) framework on a robust sample of 1121 visitors, the study tests the pedagogical pathways between educational exposure, ethical norm internalization, and long-term behavioral compliance. The structural analysis confirms that both formal instruction and on-site informal learning experiences—mediated by the internal adoption of ethical codes—positively and significantly influence learners’ pro-environmental behavioural learning outcomes within the protected area. Furthermore, the findings demonstrate that successful transformative place-based learning yields a profound value attachment, manifesting as long-term loyalty to the ecosystem’s values. Additionally, the structural model demonstrates a clear pathway for environmental financing, revealing that successful environmental literacy transforms tourist ecological awareness into a tangible readiness to pay ecological fees and support ecosystem preservation. The study contributes to interdisciplinary social sciences by extending place-based and experiential learning theories into environmental sociology and sustainable destination governance in non-traditional, high-pressure environments, providing actionable soft-management educational frameworks for public and institutional educators.
Earth’s frozen water reserves are inherently dynamic and play a critical role in the hydrological processes of complex, dynamic river basins. Climate-driven environmental changes have led to a significant decrease in the area and duration of seasonal snow cover, particularly in the high-altitude Asian Water Tower (Himalaya). Snow cover estimates are challenging in the high-altitude Hindu Kush-Himalayan (HKH) region, which is a core contributor to water resources that sustain the environment and diverse downstream ecosystems that support more than half of the Earth’s population. This study quantifies the snow cover area over the period of 1993–2023 across the basins of ten major snow- and rainfall-dominated rivers in the HKH region using Landsat-based Normalized Difference Snow Index (NDSI), SNOMAP, Blue Snow Threshold (BST), and Dozier and Painter methods. Additionally, this study used 178 strategically positioned points across the HKH region to explore the relationship between snow cover dynamics and environmental factors such as temperature, precipitation, and greenhouse gas concentrations. The study observed significant temporal and spatial variations in snow cover, driven by regional climatic conditions and anthropogenic influences. The results revealed declining snow cover trends of 2793.15, 2108.86, 1199.49, 247.51, 230.34, and 169.39 km2/year for the Amu Darya, Indus, Yangtze, Tarim, Mekong, Ganges, and Brahmaputra River basins, respectively. Conversely, the Salween, Yellow, and Irrawaddy River basins showed a slight increase of 1002.66, 147.06, and 20.86 km2/year, respectively. These opposing trends underline the vulnerability of snow mass to water supply and hydropower scheduling, stressing the urgent need for integrated, long-term satellite and ground-based observation platforms, as well as robust hydrological and glaciological modeling. A strategic blend of remotely sensed snow cover data and locally calibrated climate and land-use records will empower decision-makers to predict water security threats and refine reservoir operation guidelines, thereby sustaining both socio-economic and ecosystem services across the principal river corridors.
