Harnessing Multi-Source Data and Deep Learning for High-Resolution Land Surface Temperature Gap-Filling Supporting Climate Change Adaptation Activities

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(2), P. 318 - 318

Published: Jan. 17, 2025

Addressing global warming and adapting to the impacts of climate change is a primary focus adaptation strategies at both European national levels. Land surface temperature (LST) widely used proxy for investigating climate-change-induced phenomena, providing insights into radiative properties different land cover types impact urbanization on local characteristics. Accurate continuous estimation across large spatial regions crucial implementation LST as an essential parameter in mitigation strategies. Here, we propose deep-learning-based methodology using multi-source data including Sentinel-2 imagery, cover, meteorological data. Our approach addresses common challenges satellite-derived data, such gaps caused by cloud image border limitations, grid-pattern sensor artifacts, temporal discontinuities due infrequent overpasses. We develop regression-based convolutional neural network model, trained ECOSTRESS (ECOsystem Spaceborne Thermal Radiometer Experiment Space Station) mission which performs pixelwise predictions 5 × patches, capturing contextual information around each pixel. This method not only preserves ECOSTRESS’s native resolution but also fills enhances coverage. In non-gap areas validated against ground truth model achieves with least 80% all pixel errors falling within ±3 °C range. Unlike traditional satellite-based techniques, our leverages high-temporal-resolution capture diurnal variations, allowing more robust time periods. The model’s performance demonstrates potential integrating urban planning, resilience strategies, near-real-time heat stress monitoring, valuable resource assess visualize development use changes.

Language: Английский

---

From Data to Insights: Modeling Urban Land Surface Temperature Using Geospatial Analysis and Interpretable Machine Learning

Sensors, Journal Year: 2025, Volume and Issue: 25(4), P. 1169 - 1169

Published: Feb. 14, 2025

This study introduces an innovative machine learning method to model the spatial variation of land surface temperature (LST) with a focus on urban center Da Nang, Vietnam. Light Gradient Boosting Machine (LightGBM), support vector machine, random forest, and Deep Neural Network are employed establish functional relationships between LST its influencing factors. The approaches trained validated using remote sensing data from 2014, 2019, 2024. Various explanatory variables representing topographical characteristics, as well landscapes, used. Experimental results show that LightGBM outperforms other benchmark methods. In addition, Shapley Additive Explanations utilized clarify impact factors affecting LST. analysis outcomes indicate while importance these changes over time, density greenspace consistently emerge most influential attained R2 values 0.85, 0.92, 0.91 for years 2024, respectively. findings this work can be helpful deeper understanding heat stress dynamics facilitate planning.

Language: Английский

---

Spatiotemporal Changes in Evapotranspiration and Its Influencing Factors in the Jiziwan Region of the Yellow River from 1982 to 2018

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(2), P. 252 - 252

Published: Jan. 12, 2025

Evapotranspiration (ET) is a critical process in the interaction between terrestrial climate system and vegetation. In recent years, ET has undergone significant changes Jiziwan region of Yellow River Basin, primarily due to implementation ecological restoration programs dual impacts change. As result, hydrological cycle processes have been profoundly affected, making it crucial accurately capture trends its components, as well identify key drivers these changes. this study, we first systematically analyzed dynamic evolution components area 1982 2018 from perspective land use To achieve accurate simulations, introduced multiple linear regression algorithm quantitatively evaluated specific contributions five factors, including precipitation, temperature, wind speed, humidity, radiation, normalized difference vegetation index (NDVI), factor, components. On basis, explored combined influence mechanism change on detail. The results revealed that structure changed significantly evapotranspiration gradually replaced soil evaporation, occupies dominant position, become main component area. Among many factors affecting ET, contribution most significant, with an average rate approximately 59%. Moreover, human activities total also high. had greatest impact transpiration were NDVI, respectively. terms spatial distribution, eastern part was more affected by environmental changes, dramatic. This study not only enhances our scientific understanding their driving mechanisms but provides solid foundation for development water resource management strategies region.

Language: Английский

---

Spatiotemporal Patterns in the Urban Heat Island Effect of Several Contemporary and Historical Chinese “Stove Cities”

Sustainability, Journal Year: 2024, Volume and Issue: 16(7), P. 3091 - 3091

Published: April 8, 2024

Various cities in China have been identified as “stove cities” either contemporary or historical times, exposing residents to extremely high temperatures. Existing studies on the heat island effect stove are not representative nationwide. The outdated nature of these also significantly diminishes relevance their findings. Thus, reassessing urban (UHI) is necessary context global climate change and urbanization. This study focuses seven symbolic geographically distributed China, including Nanjing, Chongqing, Wuhan, Fuzhou, Beijing, Xi’an, Turpan. Using land surface temperature (LST) data, this investigates summer from 2013 2023 analyzes changes spatial distribution effect. paper utilizes impervious data clustering algorithms define suburban areas. It then examines evolution intensity (SUHII) over time. Incorporating urbanization variables like population density area, main factors affecting 2018. We find that all continuously expand, with annual average intensifying years. With exception cool effects remaining six show an overall intensification trend. From 2018, SUHII has primarily related expansion planning layout, minimal impact such density.

Language: Английский

---

Evaluating the efficiency of NDVI and climatic data in maize harvest prediction using machine learning

International Journal of Digital Earth, Journal Year: 2024, Volume and Issue: 17(1)

Published: May 28, 2024

Accurate anticipation of the maize harvest date is important in agricultural market, as it ensures sustainability food production response to increasing global demand for food. This paper proposes a predictive model determine optimal time plots using Normalised Difference Vegetation Index (NDVI) and climatological data. These variables were oversampled used train various models, including Random Forest (RF), Gradient Boosting Machine (GBM), Light (LGBM), Extreme (XGBoost), CatBoost Support Vector (SVM). Bayesian optimisation has been find best hyperparameters Shapley values identify that exert most significant influence on prediction each instance. As result this approach, with an accuracy 92.1% Area Under Curve (AUC) 0.935 was developed. The determined these results atmospheric pressure, mean temperature, precipitation, NDVI, precipitation.

Language: Английский

---

Development of downscaling technology for land surface temperature: A case study of Shanghai, China

Urban Climate, Journal Year: 2025, Volume and Issue: 61, P. 102412 - 102412

Published: April 10, 2025

Language: Английский

---

GWR–ANN modelling for spatiotemporal prediction of land surface temperature in Thanjavur delta: evaluating environmental impacts on climate action and SDGs

Environment Development and Sustainability, Journal Year: 2025, Volume and Issue: unknown

Published: April 15, 2025

Language: Английский

---

Combining remote sensing applications and local knowledge in understanding urban heat in a semi-arid region: a case study of Tamale’s thermal landscape

Local Environment, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 19

Published: April 19, 2025

Language: Английский

---

Implementation of deep learning algorithms to model agricultural drought towards sustainable land management in Namibia's Omusati region

Land Use Policy, Journal Year: 2025, Volume and Issue: 156, P. 107593 - 107593

Published: May 13, 2025

Language: Английский

---

Feasibility of Urban–Rural Temperature Difference Method in Surface Urban Heat Island Analysis under Non-Uniform Rural Landcover: A Case Study in 34 Major Urban Agglomerations in China

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(7), P. 1232 - 1232

Published: March 31, 2024

The urban–rural temperature difference is widely used in measuring surface urban heat island intensity (SUHII), where the accurate determination of rural background crucial. However, traditionally, entire permeable has been selected to represent temperature, leaving uncertainty about impact non-uniform surfaces with multiple land covers on accuracy SUHII quantification. In this study, we proposed two quantifications derived from primary (SUHII1) and secondary (SUHII2) types, respectively, which successively occupy over 40–50% whole regions. spatial integration temporal variation SUHII1 SUHII2 were compared result regions (SUHII) within 34 agglomerations (UAs) China. results showed that differed slightly SUHII, correlation coefficients SUHII1/SUHII2 are generally above 0.9 most (32) UAs. Regarding long-term between 2003 2019, three methods demonstrated similar seasonal patterns, although (or SUHII2) tended overestimate or underestimate SUHII. As for multi-year at regional scale, day–night cycle monthly variations found be identical each geographical division separately, indicating spatiotemporal pattern revealed by minimally affected diversity landcover types. findings confirmed viability LST method patterns under cover

Language: Английский

---