Publication:
Predictive modeling of land surface temperature (LST) based on Landsat-8 satellite data and machine learning models for sustainable development

Simple item page
dc.citedby29
dc.contributor.authorPande C.B.en_US
dc.contributor.authorEgbueri J.C.en_US
dc.contributor.authorCostache R.en_US
dc.contributor.authorSidek L.M.en_US
dc.contributor.authorWang Q.en_US
dc.contributor.authorAlshehri F.en_US
dc.contributor.authorDin N.M.en_US
dc.contributor.authorGautam V.K.en_US
dc.contributor.authorChandra Pal S.en_US
dc.contributor.authorid57193547008en_US
dc.contributor.authorid57204115082en_US
dc.contributor.authorid55888132500en_US
dc.contributor.authorid35070506500en_US
dc.contributor.authorid57214592076en_US
dc.contributor.authorid57224683617en_US
dc.contributor.authorid9335429400en_US
dc.contributor.authorid57687175000en_US
dc.contributor.authorid57208776491en_US
dc.date.accessioned2025-03-03T07:44:26Z
dc.date.available2025-03-03T07:44:26Z
dc.date.issued2024
dc.description.abstractAccurate prediction of Land Surface Temperature (LST) is critical for understanding and mitigating the effects of climate change and land use dynamics. This study proposes a novel approach that leverages ensemble models and correlation analysis based on Landsat-8 satellite data to forecast LST and explore its environmental relationships. Time-series satellite data spanning winter and summer seasons of 2018?2019 was retrieved from the Google Earth Engine (GEE) platform. LST, normalized difference vegetation index (NDVI), rainfall, and evapotranspiration (ET) datasets were derived from Landsat-8 data within GEE to facilitate LST modeling. The ensemble framework combines three powerful machine learning algorithms: XG-Boost, Bagging-XG-Boost, and AdaBoost, to enhance the accuracy and robustness of LST predictions. Compared to standalone models, the proposed ensemble models demonstrated significant improvements in LST prediction accuracy. While XG-Boost and AdaBoost achieved moderate accuracies with R2 values of 0.57 and 0.60, respectively, the Bagging ensemble model surpassed them with an outstanding R2 of 0.75. Furthermore, a correlation analysis by using linear regression (LR) model explored the relationships between ET, rainfall, NDVI, and LST. The analysis revealed strong positive correlations between NDVI and ET (R2 = 0.95), while correlations between NDVI and LST (R2 = 0.31) and NDVI and rainfall (R2 = 0.47) were weaker. These findings contribute significantly to our understanding of LST trends and the impact of climate change on environmental variables. Ultimately, this knowledge can inform effective sustainable decision-making in the area. ? 2024 Elsevier Ltden_US
dc.description.natureFinalen_US
dc.identifier.ArtNo141035
dc.identifier.doi10.1016/j.jclepro.2024.141035
dc.identifier.scopus2-s2.0-85185407091
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85185407091&doi=10.1016%2fj.jclepro.2024.141035&partnerID=40&md5=fa6b092fd5f29baf99b4946f4fb648b5
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/36757
dc.identifier.volume444
dc.publisherElsevier Ltden_US
dc.sourceScopus
dc.sourcetitleJournal of Cleaner Production
dc.subjectAdaptive boosting
dc.subjectAtmospheric temperature
dc.subjectClimate models
dc.subjectCorrelation methods
dc.subjectDecision making
dc.subjectForecasting
dc.subjectLand surface temperature
dc.subjectLand use
dc.subjectMachine learning
dc.subjectRain
dc.subjectSatellites
dc.subjectSurface measurement
dc.subjectSurface properties
dc.subjectSustainable development
dc.subjectEnergy
dc.subjectEnsemble models
dc.subjectGoogle earth engine
dc.subjectGoogle earths
dc.subjectLand surface temperature
dc.subjectLANDSAT
dc.subjectMachine-learning
dc.subjectNormalized difference vegetation index
dc.subjectSatellite data
dc.subjectSDG
dc.subjectClimate change
dc.titlePredictive modeling of land surface temperature (LST) based on Landsat-8 satellite data and machine learning models for sustainable developmenten_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS