Climate change is a critical global issue, and understanding regional temperature trends is essential for effective mitigation and adaptation strategies.Rising temperatures, driven by climate change and anthropogenic activities, are altering hydrological cycles, weather patterns, and environmental systems (Chi et al., 2023).Over the past few decades, climate change has significantly affected agricultural productivity worldwide (Yadav et al., 2020).Increasing climate variability and frequent extreme weather events have become major challenges for sustainable development and food security (Gregory et al., 2005).Rising temperatures have also intensified evapotranspiration, amplified agricultural droughts and increased crop water demand, which has led to severe water scarcity in several Indian regions (Singh, 2019).To study climatic trends, both parametric and non-parametric statistical methods such as the Mann-Kendall test, Theil-Sen slope estimator, and linear regression have been widely applied (Abdulfattah et al., 2025;Swami, 2024;Sridhara and Pradeep, 2021).The Hyderabad-Karnataka region in southern India exemplifies an area where assessing temperature trends is vital.Understanding these patterns provides critical insights into climate impacts and supports strategies for sustainable development and regional climate adaptation (Kalli and Jena, 2023).The Hyderabad-Karnataka region is the northeastern part of state of Karnataka comprising six districts (Bidar, Kalaburgi, Yadgir, Raichur, Koppal and Bellari) sharing the eastern boundaries with the states of Telangana and Andhra Pradesh and lies between latitudes 1460' to 1830' North and longitudes 7560' to 7770' East.It is now known as Kalyana Karnataka region, renamed in 2019 to move away from its colonial association and reflect a new era of development.The climate of the region is predominantly dry for most of the year, with extremely hot summers reaching temperatures of up to 45C.The hot summer begins in mid-February and lasts until the end of May.The region receives rainfall from both the South-West and North-East monsoons, with an average annual rainfall of 692 mm.Evaporation rates in the region vary significantly, reaching a high of 9.0 mm day -1 during summer and dropping to 1.1 mm day -1 in winter.The temperature data utilized for the current study was sourced from the NASA POWER (https://power.larc.nasa.gov/)database, specifically focusing on average temperature records of six districts (Bidar, Kalaburgi, Yadgir, Raichur, Koppal and Bellari) spanning a period of 42 years, from 1981 to 2022.The raw data was processed and aggregated into monthly and seasonal averages.The seasons were categorised as kharif (June to September), rabi (October to February) and summer (March to May).The long-term temperature trends were analyzed using the non-parametric Mann Kendall test (Mann, 1945;Kendall, 1975).The details of MK test analysis are presented by several workers (Abdulfattah et al., 2025;Swami, 2024).The Mann Kendall trend analysis (Table 1) revealed a

Effective pest management relies on early and accurate forecasting, yet current models struggle to capture regional specific complex relationship between weather conditions and pest incidence. This study addresses this gap by developing a robust crop pest forecasting model using the Group Method of Data Handling (GMDH) regression. We employed three decomposition techniques like Empirical Mode Decomposition (EMD), Ensemble Empirical Mode Decomposition (EEMD), and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) to break down nonlinear data into Intrinsic Mode Functions (IMFs). These IMFs were then predicted using GMDH regression, incorporating weather variables as independent factors. The ensemble forecasts were constructed by aggregating the predicted IMFs. The study utilized pest incidence data from 2015 to 2023 for aphid, jassid, thrips, and whitefly pests. Findings indicated that the CEEMDAN-GMDH model outperformed others for forecasting the incidence of aphid, thrips, and whitefly pests, with improvements of 16.3%, 4.3%, and 13.6% over the univariate GMDH model, respectively. For jassid, the EEMD-GMDH model provided the best forecasts, despite CEEMDAN’s superior decomposition capabilities. The study concludes that integrating decomposition methods, with GMDH regression provides a more reliable tool for predicting pest incidences in cotton crops, thereby aiding in better pest management strategies.

Forewarning pests and diseases in real-time is one of the key components in Agromet Advisory Bulletin (AAB) of India Meteorological Department (IMD). In order to facilitate it, a comprehensive knowledge databank on weather-based pests and diseases of crops were collected to develop a decision support system (DSS) comprising of algorithms on thumb rules of pests and diseases prediction of major crops of kharif and rabi seasons. The algorithm was validated with the real-time observation on pests and diseases of five crops (rice, sorghum, chickpea cotton and maize) during rabi 2021-22 and kharif 2022 seasons, grown over 12 District Agromet Units (DAMU) locations across the country. The DSS upon validation, yielded prediction of pest diseases with correctness varying between 33 to 100 percent across the crops and locations. The forecast accuracy was more reliable during rabi season in comparison to kharif season crops/pests/diseases. For effective operationalization of weather based heuristic models and thumb rules, these have to be tested and validated in all the agroclimatic zones of the country.

Air pollution in coastal urban environments is a complex interplay of emission sources and meteorological conditions, often inadequately captured by traditional horizontal monitoring. This study investigates the vertical distribution of major air pollutants PM2.5, PM10, SO₂, NO2, NO and CO across five high-rise multi-storey buildings in Rushikonda, Visakhapatnam, during summer and winter seasons. Over 30 days of continuous monitoring with a distinct vertical gradient, where noticeable variations were observed, particularly for particulate matter, with PM2.5 and PM10 concentrations decreasing by up to 10.2% and 15.4%, respectively, from ground to elevated levels. However, statistical data analysis and 3-D visualization of the relationship between the pollutants and the meteorological parameters revealed critical thresholds for temperature, relative humidity (RH), and height influencing pollutant stratification. 3D surface visualizations further emphasized RH's role in enhancing particulate concentrations via hygroscopic growth and suppressing vertical dispersion, besides the long-range transport of air mass could also contribute to the high concentration values of particulate matter. The findings highlight the utility of vertical monitoring using existing urban infrastructure and underscore its relevance in refining air quality management in coastal cities.

Global climate models (GCM) are effective in representing climate processes at the global scale; however, they often exhibit biases and limited accuracy at the local scale. This limitation is particularly critical in monsoon-dominated regions such as West Java, where statistical downscaling (SD) provides an appropriate approach. This research aims to predict monthly rainfall in West Java using the Bayesian Tweedie Compound Poisson Gamma (TCPG) model with combined scenarios of bias correction and dummy variables. Bias correction used empirical quantile mapping (EQM) with CHIRPS data. Monthly rainfall as the response variable was modelled using a Bayesian TCPG regression, with parameter estimation performed through Bayesian Markov chain Monte Carlo (MCMC) using the Metropolis Hastings algorithm. The best model scenario was achieved using dummy variables without bias correction, with CNRM-ESM2-1 identified as the most effective Decadal Climate Prediction Project (DCPP) model. These findings enhance rainfall prediction accuracy in tropical monsoon regions and support agricultural and water resource planning in West Java.

Abiotic stressors have a significant impact on crop productivity, with moisture stress being especially important. This study investigates the consequent shifts in sorghum yields in Senegal, using NASA Power and CHIRPS data from 1990 to 2024. Matam, Mbane, Gamadji Sarre, and Yang-Yang were identified as hotspots by the Rainfall Anomaly Index (RAI) with low rainfall, exhibiting only 12–15% rainy days. Precipitation was categorized into Above-Normal (AN) or Below-Normal (BN) using the Rainfall Anomaly Index (RAI; AN if RAI ≥ 0, BN if RAI < 0). Sorghum yields were notably lower during BN years. APSIM model was used to assess the impact of fertilizer doses (40 kg ha-1 and 60 kg ha-1) and sowing dates on yield variations. The results indicate minimal yield fluctuation with increased fertilizer within recommended limits and highlight that reliable rainfall forecasts (80% or greater accuracy) can significantly influence farm-level decision-making. These findings emphasize the crucial role of rainfall variability in agricultural planning and climate adaptation strategies.

Agriculture is the primary driver of Indian economy and country's GDP growth.Forecasting of agricultural production is an essential element for efficient resource management.Rice is primary crop grown in Dakshina Kannada District for three distinct seasons, each having its own set of climatic conditions.Furthermore, this region receives maximum rainfall and experiences fluctuations in monsoon intensity.This generates complex models in predicting rice crop yield.The machine learning (ML) techniques have proven effective in modelling using both historical and current data to predict crop yield (Aljuaydi and Wu 2022).ML algorithms like Random Forest (RF), Support Vector Machines (SVM), k-Nearest Neighbours (kNN) and Artificial Neural Networks (ANN) are used to predict crop growth (Shawon et al., 2024).As example, ML models can analyze hidden relationships between soil health parameters and climatic variables (Zou and Okhrin 2024).Development of crop yield models for seasons-based agriculture is crucial (Paudel, 2020).In rabi season, the crop exhibits stability during its growth, while in Kharif seasons, the yields become erratic due to monsoon fluctuations (Mohapatra et al., 2023).

Reference evapotranspiration (ETo) is crucial for calculating irrigation requirements. Instruments that directly measure ETo are still costly and limited while the empirical models are data intensive. Meteorological data of Central Luzon, Philippines (1985-2019) were used to estimate ETo using the FAO Penman-Monteith method. The performances of machine learning algorithms in estimating ETo were analyzed using ground-based weather data. Optimal models were determined using decision thresholds (RMSE<0.39 mm day-1, R2>0.75, MSE<0.15 mm day-1, MAE<0.30 mm day-1). The models were further assessed using principal component analysis for finding relevant variables (σ2=0.95) and the Wilcoxon test for comparing two samples (α=0.05). Results show that optimal model required only two or three weather variables depending on the station. In general, the algorithms can be ranked as follows: Gaussian progress regression, Neural network, Support vector machines, Ensemble of trees, Regression trees, and Linear regression. The study reveals that machine learning can accurately predict ETo using ground-based weather data, and it can be a good alternative to data-intensive empirical models.