Accurate and early predictions in agriculture are essential for sustainable farming and optimizing field management. Crop yield prediction significantly impacts the farmer's decisions on crop insurance, storage demand and other important factors during the growing season. Due to non-linearity in crop yield, the use of non-linear models for forecasting purposes has become popular these days. In this paper, ANN and LSTM models were trained using weather parameters to forecast the cotton yield for Punjab, AIndia. Predicting the yield with minimum error is aAmain challenge. ANN (10 10 10 1) Amodel with ReLU activation function in hidden layers performed better thanAother forecasting models with a minimum MSE (0.0182). AThe analysis using the NN model concluded that the weather parameters played an important role in affecting the plant growth. AThese variables may enhance or reduce the yield significantly. Sensitivity analysis showed that relative humidity was the most important weather parameter followed rainfall.
An unprecedented heat wave lasting approximately two weeks occurred in Odisha during the third and fourth weeks of May 2015, Aresulting in meteorological hazards. In this study, an extreme temperature event (ETE) occurred on 25-27th May 2015, Awith about 15 meteorological observation stations in the state of Odisha recording maximum temperatures exceeding 45 degrees C, Aresulting in an intense heat wave. TheAmesoscale modeling framework (WRF4.0) is configured and optimized to simulate ETE at the regional scale in this study using different land-use scenarios. The maximum temperature from a time-ensemble simulation using the current land-use scenario based on Indian Space Research Organization (ISRO) data is found to be more accurate than simulations based on US Geological Survey (USGS) data at India Meteorological Department (IMD) meteorological stations. The mean percentage errors of simulated maximum temperatures over Odisha with respect to IMD station-scale observations are 1.6% (ISRO) and 3% (USGS) on 25th May 2015, and 4.2% (ISRO) and 4.7% (USGS) on 26th May 2015, respectively. Compared with the simulation based on ISRO data (more urbanized), the simulated horizontal surface wind at the different locations in Odisha is generally higher in the simulation based on USGS data. Changes in land use increase the roughness length, reducing surface wind speed. The dynamical aspects are also explored by analyzing humidity, outgoing longwave radiation (OLR), Convective Available Potential Energy (CAPE), and Convective Inhibition (CIN), etc., from the model and validated with the reanalysis products, which support the model performance in capturing the conducive environment resulting in a regional heat wave. The land use analysis reveals that the state-wide increase in urbanization between 1992 and 2015 was about 0.4%, with the highest percentage increase occurring in cities like Bhubaneswar, Sambalpur, Jharsuguda, and Rourkela in the Sundergarh district, which regularly experience the heat wave in the month of May, and the same are accurately simulated by the optimized and calibrated model configuration. Land-use change, including urban expansion and shifting cropping patterns, along with increased anthropogenic activities, is directly linked to the rise in maximum temperatures.
The National Centre for Medium Range and Weather Forecasting (NCMRWF) operated the MIHIR High-Performance Computing (HPC) Facility, delivering up to 2.8 petaflops of processing capacity to run Numerical Weather Prediction (NWP) models, thereby enabling accurate and timely weather forecasting. This study presents a comprehensive performance profiling and optimization analysis of the NCMRWF Unified Model (NCUM) version 13.0 on the MIHIR Cray XC40 HPC Facility. The model requires computations in the order of peta floating-point operations per second (PFLOPS). AThe NCUM is profiled at two horizontal resolutions n96e (similar to 130 km) taken as baseline and n1280e (similar to 10 km) using the Cray Performance Analysis Tool (CrayPAT) to identify runtime bottlenecks and communication overhead. The optimization experiments focused on halo size reduction, domain decomposition strategies, OpenMP threading, and MPI rank reordering. Results demonstrate that reducing the extended halo size from 10 to 5 grid points improves execution time by similar to 10 seconds and thus reduces communication costs and lowers imbalance in key routines from 15.2% to 3.8%. A change in domain decomposition from 4 & times;8 to 3 & times;12 further reduced MPI collective imbalance, while rank reordering improved execution time by up to 12.8%. These findings will be valuable in guiding domain and communication optimizations to efficiently scale high-resolution NWP models on the Cray XC40 system and future HPC architectures to be deployed at NCMRWF.
Climate variability, particularly fluctuations in temperature and rainfall, showed significant impacts on the agricultural sector, especially on cropping systems critical to ensuring food security. A comprehensive study assessed the influence of both positive and negative climate variability on agriculture and horticulture in the Sirmour district of Himachal Pradesh. This investigation analyzed the complex relationship between climate variables and crop productivity over 27 yearsA(1995-2021), Aproviding insights crucial for developing climate-resilient farming strategies. The statistical tools and models were employed to evaluate long-term trends in key climatic variables, with a focus on determining the significance and rate of observed changes. Over the study period, a significant decline in both maximum and minimum temperatures during the Kharif (summer) season was observed, with rates of-0.080 degrees C/year andA-0.090 degrees C/year, respectively. Trend analysis of Kharif crops indicated a significant increase in the productivity of rice (0.046 t/ha/year) and pulses (0.020 t/ha/year), Awhile maize showed aAnon-significant increase in productivity. In the horticulture sector, significant declines in both maximum and minimum temperatures were observed during the fruit-setting stage in the temperate zone, suggesting climate-induced alterations across multiple phenological stages. Furthermore, in the sub-tropical region, a significant decrease in maximum temperature was recorded during the fruit-setting stage. These findings indicate that over the past 27 years, climatic changes in the Sirmour district have had a generally positive impact on the productivity of most fruit crops, except guava, which exhibited a decline in yield. This analysis highlighted the critical need for adaptive strategies in the face of evolving climate patterns to sustain and enhance agricultural productivity in the region.
This study investigates the causes of riverbank erosion along the Hau Bassac River in Hoa Lac commune, An Giang province, Vietnamese Mekong Delta (VMD), based on integrating hydrodynamic, sediment, and morphology characteristics. Field data collected in November 2024, representing receding flood season conditions, indicate that high flow velocities, especially on the outer banks of meanders, frequently approached or exceeded calculated permissible non-eroding velocities. Steep bank slopes (> 50 degrees), erodible alluvial materials, and tidal fluctuations further contribute to instability. While regional factors like upstream damming and sand mining exacerbate systemic vulnerability, our findings pinpoint the critical role of local concentrated flow energy and geotechnical weaknesses. The analysis reveals a multi-stage failure mechanism, where extreme velocities during peak floods likely act as the primary trigger for basal scour, while sustained, near-threshold flows during the receding season prevent natural recovery and perpetuate bank instability. This study provides a critical snapshot of erosion mechanisms that are likely intensified during peak flood events, offering essential data for local mitigation and emphasizing the need for continued field-based monitoring in this dynamic river system.
