Stubble burning in Punjab, India, poses significant environmental challenges, particularly impacting air quality. This study aims to examine the spatial and temporal patterns of stubble burning events and their potential effect on ambient air quality from 2019 to 2022. High-resolution Sentinel-2 satellite imagery was employed to delineate the spatial extent of stubble burning. Burnt areas were identified using the Normalised Burn Ratio (NBR). Air quality was evaluated based on PM2.5 and PM10 concentrations data obtained from the Punjab Pollution Control Board. The Inverse Distance Weighting (IDW) interpolation technique was used to estimate pollution values in areas lacking direct monitoring. The study revealed significant year-to-year variations in areas affected by stubble burning. The smallest burnt areas were recorded in October 2019 and 2021 (209 sq km), while the largest was in 2020 (755.38 sq km). In every year studied, the burnt area in November consistently exceeded that in October, with the largest area (10315 sq km) observed in 2021. PM2.5 and PM10 concentrations also showed annual fluctuations, with the highest recorded in 2020 and 2021. In particular, in October 2020, higher PM2.5 and PM10 levels were detected in the eastern region of Punjab. November consistently exhibited higher PM2.5 and PM10 concentrations than October for all years analysed, peaking in 2021. The spatial and temporal variations of stubble burning events and their relationship with air quality highlight the need for targeted interventions. Understanding these patterns is crucial for mitigating the adverse effects of stubble burning on air quality in Punjab, India. Future research should focus on evaluating the effectiveness of various mitigation strategies.
In this research, the SWAT+ model was employed to elucidate hydrological dynamics within the Beas Basin. The primary objectives encompassed the calibration of the SWAT model for accurate water balance quantification, annual simulation of salient hydrological components, and a decadal analysis of trends in fluvial discharge and sediment transport. The methodology encompasses simulating hydrological data with the SWAT+ model, followed by calibration and validation using flow data from Larji and Mahadev hydroelectric plants. The model’s efficacy in depicting streamflow and other hydrological components is corroborated by statistical measures such as the Nash–Sutcliffe efficiency and PBIAS. The water balance analysis delivers insights into the basin’s hydrological characteristics, including surface flow, water yield, and evapotranspiration. The temporal analysis exposes intricate seasonal and interannual variability in flow and sediment discharge, while spatial distribution highlights heterogeneity across the basin. These findings have practical implications for water resource management, including optimizing water allocation, hydroelectric power generation, irrigation, and environmental concerns. Limitations, such as data quality and model simplifications, are acknowledged, and future data collection and observations are recommended for improved model performance. In essence, these researches enhance understanding of the Beas Basin’s hydrology, setting a course for future investigations to integrate more data sources, refine model parameters, and consider climate and land-use changes for a richer comprehension of the basin’s hydrological dynamics.
Crop growth monitoring at various growth stages is essential for optimizing agricultural inputs and enhancing crop yield. Nitrogen plays a critical role in plant development; however, its improper application can reduce productivity and, in the long term, degrade soil health. The aim of this study was to develop a non-invasive approach for nitrogen estimation through proxies (Nitrogen Flavanol Index) in Mentha arvensis using UAV-derived multispectral vegetation indices and machine learning models. Support Vector Regression, Random Forest, and Gradient Boosting were used to predict the Nitrogen Flavanol Index (NFI) across different growth stages. Among the tested models, Random Forest achieved the highest predictive accuracy (R2 = 0.86, RMSE = 0.32) at 75 days after planting (DAP), followed by Gradient Boosting (R2 = 0.75, RMSE = 0.43). Model performance was lowest during early growth stages (15–30 DAP) but improved markedly from mid to late growth stages (45–90 DAP). The findings highlight the significance of UAV-acquired data coupled with machine learning approaches for non-destructive nitrogen flavanol estimation, which can immensely contribute to improving real-time crop growth monitoring.
Crop growth monitoring during its growth stages is essential for optimizing agricultural resource inputs and enhancing crop productivity. Nitrogen plays a critical role during plant growth but its improper application not only reduces the crop productivity but also in the long turn cause soil degradation. This study addresses an advanced and integrated approach to develop a non-invasive mechanism for nitrogen estimation through proxies (Nitrogen Flavanol Index) in Mentha arvensis. This study integrates UAV-based multispectral imagery vegetation indices, field observed non-invasive data, and machine learning (ML) models to predict NFI during growth stages of Mentha arvensis. Machine learning models (Support Vector Regression, Random Forest, and Gradient Boosting) were evaluated, with Random Forest achieving highest accuracy (R² = 0.86, RMSE = 0.32), followed by Gradient Boosting (R² = 0.75, RMSE = 0.43) at 75 Days After Planting (DAP). Model performances were observed to be lowest at early growth stages (15–30 DAP), however, it improved significantly from mid to late growth stages (45–90 DAP). The findings highlight the significance of UAV-acquired data coupled with machine learning approaches for non-destructive nitrogen flavanol estimation, which can immensely contribute to improved real-time crop growth monitoring.