Academic Departments

Permanent URI for this community

http://nitt.ndl.gov.in/handle/123456789/30

Browse

Browsing Academic Departments by Author "Arunab, K.S."

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Exploring spatial machine learning techniques for improving land surface temperature prediction
    (Elsevier B.V., 2024-05-05) Arunab, K.S.; Mathew, Aneesh
    Land Surface Temperature (LST) is a crucial parameter in Earth observation and environmental studies due to its significance in various fields. The purpose of this study is to investigate the effects of including spatial information into the Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) models for forecasting LST. The significance and impact of each input parameter on the models' predictive capabilities are assessed using the SHAP (Shapley Additive exPlanations) approach and the model intercomparisons were done using the error evaluation metrices. The predictions were further validated using the Pearson correlation, independent samples t-test and potential geographic anomalies in the predictions are examined by spatial comparison of predicted errors using classification maps and error envelopes. The projected errors are within the acceptable range and range from −2.267 °C to 1.292 °C for the spatially enhanced RF model and from −1.675 °C to 1.439 °C for the spatially enhanced XGBoost model. These error ranges closely align with the training data's quality flag of ±2 °C, demonstrating the models' capability to predict LST accurately and within a reasonable error range. The findings show the significance of adding spatial information for precise LST prediction and draw attention to possible uses for such models in environmental monitoring and management. The work advances our understanding of spatial modelling strategies and offers practical guidelines for enhancing LST forecasts.
  • No Thumbnail Available
    Item
    Urban heat island and pollutant correlations in Bangalore, India using geospatial techniques
    (Elsevier Ltd, 2025-01-28) Mathew, Aneesh; Arunab, K.S.
    The interaction between urban heat island (UHI) effects and urban air pollution significantly impacts urban ecology, climate dynamics, and inhabitants' well-being. This study examines into the correlation between UHI effects and various pollutants (CO, HCHO, aerosols, NO2, O3, and SO2) across Bangalore from 2019 to 2022, exploring their spatial and thermal connections. The study utilized satellite remote sensing data from TROPOMI for air pollutants (CO, NO₂, HCHO, SO₂, O₃, and aerosols) and MODIS for land surface temperature (LST). Data were collected over a four-year period (2019–2022) to analyze spatial and temporal pollutant distributions and UHI effects in Bangalore and employed statistical methods, including Pearson correlation, independent t-tests, and ANOVA, to assess the relationships between UHI indicators and pollutant concentrations. A weighted Urban Pollution Island (UPI) index was developed using Fuzzy AHP, while thermal categorization was achieved through spatial analysis techniques. Research indicates significantly elevated pollution levels in urban areas compared to rural regions. The research demonstrates positive correlation between UHI indicators and CO, HCHO, aerosols, NO2, and O3 in urban-rural environments. A negative correlation is observed between the UHI indicator and SO2 in these contexts, requiring a thorough investigation of the UHI-pollutant relationship. High-risk zones (HRZs) demonstrate significantly elevated yearly average concentrations of NO2 (66.614%), aerosols (13.610%), HCHO (8.816%), and CO (2.028%) relative to low-risk zones (LRZs). Ozone levels are consistently similar between HRZs and LRZs. In contrast, LRZs demonstrate a greater yearly average concentration of SO2 (7.562%) than HRZs. Furthermore, HRZs exhibit an elevated LST of 2.198 °C relative to LRZs. These results yield essential insights for urban planning and policy development, providing a thorough comprehension of UHI pollution dynamics. This research clarifies these dynamics, aiding informed decision-making to mitigate the effects of UHI and pollution in urban settings