Remote Sensing Applications-Society and Environment最新文献

{"title":"Hybrid Naïve Bayes Gaussian mixture models and SAR polarimetry based automatic flooded vegetation studies using PALSAR-2 data","authors":"Samvedya Surampudi,&nbsp;Vijay Kumar","doi":"10.1016/j.rsase.2024.101361","DOIUrl":"10.1016/j.rsase.2024.101361","url":null,"abstract":"<div><div>Flood mapping using Synthetic Aperture Radar (SAR) data impose limitations in fully distinguishing flood under vegetation due to false double bounce returns from inundated tree trunks along with seasonal heterogeneities devised from changing land cover settings. In addition, rapid mapping of flooded vegetation is challenging during near real time applications. In this paper a fully automatic novel supervised classification approach called polarimetric Naïve Bayes is proposed that combines polarimetric information with series of Gaussian mixture models in Naïve Bayes framework to detect various flooded vegetation classes. It also allows the user to choose class configuration and eliminates creation of Region of Interest (ROI) for supervised training. The proposed approach uses scattering information from pre monsoon PolSAR dataset in training step to create ROIs for buildings and other features. In the next step series of Gaussian Mixtures are used for density estimation for different features in Bayesian multiclass problem. The newly developed classifier applied on 2016 Assam flood event resulted in precise mapping of at least three different vegetation classes under flood such as submerged vegetation, wetlands and floating vegetation. Under optimal class configuration, the approach showed better performance compared to other supervised techniques applied on the same data set such as MLE, Mahalanobis, Minimum Euclidean distance, and SVM classifications in delineating flood, submerged vegetation, wetlands and floating vegetation with Producer’s Accuracy of 98.6%, 81.1%, 94% and 51.5% respectively and combined Overall accuracy of 95.5% for flooded vegetation class. This method also detected multiple vegetation classes with better accuracy compared to similar methods.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"36 ","pages":"Article 101361"},"PeriodicalIF":3.8,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142663075","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unveiling soil coherence patterns along Etihad Rail using Sentinel-1 and Sentinel-2 data and machine learning in arid region","authors":"Sona Alyounis ,&nbsp;Delal E. Al Momani ,&nbsp;Fahim Abdul Gafoor ,&nbsp;Zaineb AlAnsari ,&nbsp;Hamed Al Hashemi ,&nbsp;Maryam R. AlShehhi","doi":"10.1016/j.rsase.2024.101374","DOIUrl":"10.1016/j.rsase.2024.101374","url":null,"abstract":"<div><div>This research applies machine learning to predict soil coherence for Etihad Rail, marking the first comprehensive study in the United Arab Emirates (UAE)'s arid regions. By integrating Sentinel-1 SAR and Sentinel-2 data with MODIS Aerosol Optical Depth (AOD) observations, the study develops detailed models that depict complex soil coherence patterns crucial for urban planning and risk assessment. Findings show variations in soil coherence between operational and under-construction phases, influenced by seasonal changes in aerosol dynamics and sand dust levels. Higher soil coherence is linked with lower annual sand dust deposition and AOD measurements, emphasizing the importance of this data for informed decision-making. The study employs a unique combination of data sources and machine learning algorithms to predict soil coherence, including Support Vector Machine (SVM), Extreme Gradient Boosting (XGBOOST), Gaussian Process Regression (GPR), Random Forest (RF), and 1D Convolutional Neural Network (CNN), with the Random Forest model achieving the lowest root mean squared error (RMSE) of 0.0826. These contributions enhance our understanding and provide a valuable framework for infrastructure development in similar environments.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"36 ","pages":"Article 101374"},"PeriodicalIF":3.8,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142663073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Recent trends in moisture conditions across European peatlands","authors":"Laura Giese ,&nbsp;Maiken Baumberger ,&nbsp;Marvin Ludwig ,&nbsp;Henning Schneidereit ,&nbsp;Emilio Sánchez ,&nbsp;Bjorn J.M. Robroek ,&nbsp;Mariusz Lamentowicz ,&nbsp;Jan R.K. Lehmann ,&nbsp;Norbert Hölzel ,&nbsp;Klaus-Holger Knorr ,&nbsp;Hanna Meyer","doi":"10.1016/j.rsase.2024.101385","DOIUrl":"10.1016/j.rsase.2024.101385","url":null,"abstract":"<div><div>Peatlands play a key role in climate change mitigation strategies and provide multiple ecosystem services, presuming near natural, waterlogged conditions. However, there is a lack of knowledge on how spatially heterogeneous changes in climate across Europe, such as the predicted increase in drought frequency in Central Europe, might affect these ecosystem services and peatland functioning. While analysis of peat cores and moisture sensors provide high-quality insights into past or present hydrological conditions, this information is usually only available for a limited number of locations. Satellite remote sensing is an effective method to overcome this limitation, providing spatially continuous and temporally highly resolved environmental information.</div><div>This study proposes to use freely available data from the Landsat Mission to analyze trends in proxies of surface moisture of European peatlands over the last four decades. Based on a large random sample of peatland sites across Europe, we performed a pixel-wise trend analysis on monthly time-series dating back to 1984 using the Normalized Difference Water Index as a moisture indicator.</div><div>The satellite-derived moisture changes indicated a pronounced shift towards wetter conditions in the boreal and oceanic region of Europe, whereas in the temperate, continental region, a high proportion of peatlands experienced drying. Small-scale patterns of selected sites revealed a high spatial heterogeneity, the complexity of hydro-ecological interactions, and locally important environmental and anthropogenic drivers affecting the moisture signal. Overall, our results support the expected effects of current climate trends of increasing precipitation in boreal northern and oceanic north-western Europe and increasing frequency of drought in continental Europe.</div><div>Our fully reproducible approach provided new insights on continental and local scales, relevant not only to a better understanding of moisture trends in general, but also to practitioners and stakeholders in ecosystem management. It may thus contribute to developing a cost-effective long-term monitoring strategy for European peatlands.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101385"},"PeriodicalIF":3.8,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Uncovering true significant trends in global greening","authors":"Oliver Gutiérrez-Hernández ,&nbsp;Luis V. García","doi":"10.1016/j.rsase.2024.101377","DOIUrl":"10.1016/j.rsase.2024.101377","url":null,"abstract":"<div><div>The global greening trend, marked by significant increases in vegetation cover across ecoregions, has attracted widespread attention. However, even robust traditional methods, like the non-parametric Mann-Kendall test, often overlook crucial factors such as serial correlation, spatial autocorrelation, and multiple testing, particularly in spatially gridded data. This oversight can lead to inflated significance of detected spatiotemporal trends. To address these limitations, this research introduces the True Significant Trends (TST) workflow, which enhances the conventional approach by incorporating pre-whitening to control for serial correlation, Theil-Sen (TS) slope for robust trend estimation, the Contextual Mann-Kendall (CMK) test to account for spatial and cross-correlation, and the adaptive False Discovery Rate (FDR) correction. Using AVHRR NDVI data over 42 years (1982–2023), we found that conventional workflow identified up to 50.96% of the Earth's terrestrial land surface as experiencing statistically significant vegetation trends. In contrast, the TST workflow reduced this to 38.16%, effectively filtering out spurious trends and providing a more accurate assessment. Among these significant trends identified using the TST workflow, 76.07% indicated greening, while 23.93% indicated browning. Notably, considering areas (pixels) with NDVI values above 0.15, greening accounted for 85.43% of the significant trends, with browning making up the remaining 14.57%. These findings strongly validate the ongoing global greening of vegetation. They also suggest that incorporating more robust analytical methods, such as the True Significant Trends (TST) approach, could significantly improve the accuracy and reliability of spatiotemporal trend analyses.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101377"},"PeriodicalIF":3.8,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Classification of soil horizons based on VisNIR and SWIR hyperespectral images and machine learning models","authors":"Karym Mayara de Oliveira ,&nbsp;João Vitor Ferreira Gonçalves ,&nbsp;Renan Falcioni ,&nbsp;Caio Almeida de Oliveira ,&nbsp;Daiane de Fatima da Silva Haubert ,&nbsp;Weslei Augusto Mendonça ,&nbsp;Luís Guilherme Teixeira Crusiol ,&nbsp;Roney Berti de Oliveira ,&nbsp;Amanda Silveira Reis ,&nbsp;Everson Cezar ,&nbsp;Marcos Rafael Nanni","doi":"10.1016/j.rsase.2024.101362","DOIUrl":"10.1016/j.rsase.2024.101362","url":null,"abstract":"<div><div>The use of spectral signature to classify soil horizons and orders is becoming increasingly popular in the field of geotechnology. With the introduction of precise sensors and robust models for obtain data and classifying attributes, the traditional surveys can be improved with a computational analytical approach. Despite the benefits, few authors have addressed the classification of soil horizons given the budget and time-consuming required to obtain and analyze data. This study aimed to assess the efficiency of combining soil spectral reflectance (obtained by two hyperspectral imaging sensors) with robust ML (machine learning) models for classifying soil horizons. Six monoliths were collected from soil profiles located in the central northern region of Parana State, Brazil. The monoliths were scanned by VIS-NIR and SWIR hyperspectral cameras in the laboratory. Spectral signatures were obtained and explored by principal component analysis (PCA). The spectral data were subdivided into training (70%) and test (30%) sets and subjected to the random forest (RF), support vector machine (SVM), and K-nearest neighbors (KNN) methods for the classification of soil horizons. The overall accuracy, F1-score, and confusion matrix were used to verify the performance of the models. There was a significant influence of particle size and soil organic carbon on the spectral signature of the soils. Despite the data overlap between adjacent horizons observed in the PCA, the machine learning models were able to classify the horizons with promising accuracy and PCA explained the dataset with a percentage above 98%. For VIS-NIR spectra, the accuracies varied between 81.4% (KNN) and 89.9% (RF), and the F1-scores varied between 51.9% (SVM) and 78.3% (RF). For the SWIR spectra, the variation in accuracy was between 72.1% (SVM) and 86.5% (RF), but the variation in the F1-score was between 61.9% (SVM) and 85.4% (RF). These results demonstrate the promising potential of using hyperspectral imaging and machine learning models combined with traditional soil classification methods as tools.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"36 ","pages":"Article 101362"},"PeriodicalIF":3.8,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142357031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Soil and vegetation types are predisposition factors controlling greenness changes: A shift of paradigm in greening and browning modelling?","authors":"Luís Flávio Pereira ,&nbsp;Elpídio Inácio Fernandes-Filho ,&nbsp;Lucas Carvalho Gomes ,&nbsp;Daniel Meira Arruda ,&nbsp;Guilherme Castro Oliveira ,&nbsp;Carlos Ernesto Gonçalves Reynald Schaefer ,&nbsp;José João Lelis Leal de Souza ,&nbsp;Márcio Rocha Francelino","doi":"10.1016/j.rsase.2024.101366","DOIUrl":"10.1016/j.rsase.2024.101366","url":null,"abstract":"<div><div>Increases (greening) and losses (browning) of vegetation greenness related to climatic and anthropic changes are processes well documented in the literature. However, the control exerted by predisposition factors on the response of vegetation to these changes has been little studied, and appears to be especially important in anthropized regions. The present study aimed to map greening and browning processes, as well as to characterize and analyze their distribution in heavily anthropized regions regarding two main predisposition factors: soil and vegetation types. The Brazilian Semiarid region was used as a model area, using two novel approaches: a readily reproducible cloud computing approach to map consistent greening and browning processes, and a disaggregation approach in homogeneous units of vegetation, soil and land use types. The results showed that stable greenness dominates (66.8%), but browning is more frequent (29.1%) and intense than greening (4.1%), and may be related to desertification processes in native and anthropized areas. The distribution of greening and browning processes is zonal and heterogeneous. Environmental predisposition factors, mainly the water supply capacity, regionally control the distribution of greening and browning zones. Human-environment interplays locally regulate the intensity and distribution of the processes. We defend the need of a paradigm shift in greening and browning modelling. Further studies should consider the simultaneous and balanced use of predictors related to both predisposition and changes. The need for advances in the interpretability of these models is also evident, given that current approaches fail to elucidate the regulating mechanisms of greening and browning processes.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"36 ","pages":"Article 101366"},"PeriodicalIF":3.8,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142320184","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Satellite-based measurements of temporal and spatial variations in C fluxes of irrigated and rainfed cotton grown in India","authors":"Desouza Blaise ,&nbsp;Nirmala D. Desouza ,&nbsp;Amarpreet Singh","doi":"10.1016/j.rsase.2024.101365","DOIUrl":"10.1016/j.rsase.2024.101365","url":null,"abstract":"<div><div>The small number of carbon dioxide (CO₂) observation networks and the prohibitively high equipment cost restrict the estimation of net ecosystem CO₂ exchange (NEE). Satellite-based remote sensing techniques have made it possible to obtain NEE and component carbon (C) fluxes. One-third of the world's cotton area is in India, but the information on NEE is limited. We used the Level 4 Carbon (L4_C) product from the Soil Moisture Active Passive (SMAP) mission to estimate C fluxes based on satellite-derived soil moisture, weather, and vegetation data. For our study (2018-19 to 2020-21), we chose two ecosystems (rainfed central India vs. irrigated northern India). Seasonal variations were observed in C fluxes. Gross primary productivity was the highest during the boll formation phase. This phase was the strongest sink and coincided with the highest CO₂ uptake, followed by the flowering and square formation phases. The cotton crop was a C source during the initial vegetative phase and after the boll opening. Overall, the cotton crop was a sink for atmospheric CO₂ with an average NEE value of −189.6 g C m⁻² under irrigated and −245.6 g C m⁻² in rainfed cotton. Higher ecosystem respiration in irrigated cotton resulted in lower C sink strength than rainfed cotton. Our studies indicate that the SMAP L4_C product model estimates can be used to obtain information on C fluxes in real-world situations. Moreover, such satellite-based remote sensing techniques will enable large-scale environmental monitoring with different cropping systems and support policymaking.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"36 ","pages":"Article 101365"},"PeriodicalIF":3.8,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142315577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spectrometric and remote sensing investigations of some granitic rocks in the Egyptian north Eastern Desert: Insights on environmental radiogenic heat production","authors":"Osama K. Dessouky ,&nbsp;Yasser S. Badr ,&nbsp;Mahmoud M. Hassan","doi":"10.1016/j.rsase.2024.101360","DOIUrl":"10.1016/j.rsase.2024.101360","url":null,"abstract":"<div><div>Granitic rocks dominate the Neoproterozoic outcrops in the northern Egyptian Eastern Desert, prominently featuring two main categories: Arc Granitoids (AG) and late-to post-collision granites (LPCG). The AG range from granodiorite and tonalite to quartz-diorite. In contrast, LPCG comprise syenogranite, monzogranite, and alkali-feldspar granite. This study leverages Landsat-8 remote sensing data to effectively discriminate between these rock types using several advanced image processing techniques. False color composite and decorrelation stretch methods highlighted geological and structural features, revealing distinct spectral signatures for each rock type. Principal Component Analysis and band rationing further refined distinguishing various varieties within the LPCG and detailed mapping. Supervised classification using the Support Vector Machine method yielded precise delineation of rock units. The investigated granitic rocks exhibited estimated radiogenic heat production values ranging from 6.02 to 1.41 μW/m³, surpassing the average values observed in the Earth's crust. The reason behind these noteworthy surpassing values of radiogenic heat production can be directly attributed to the relatively high Gamma-ray measurements in the LPCG outcrops. Gamma-ray spectrometric analysis indicated varying distributions of radioelements, particularly between AG and LPCG. The equivalent uranium (eU) concentrations range from 2.8 to 7 ppm in AG, while LPCG exhibited broader variability from 5.1 to 34 ppm. The equivalent thorium (eTh) values range from 16.1 to 34.1 ppm, with an overall average of 23 ppm. Conversely, within the ferruginated-silicified domains, the LPCG display slightly elevated levels of eU, reaching 31.4, 35.5, and 27.8 ppm for the monzogranites, syenogranites, and alkali-feldspar granites, respectively. These elevated levels suggest the potential for iron oxy-hydroxide minerals to adsorb uranium within alteration zones. Additionally, radioactive minerals such as zircon, columbite, uranothorite, allanite, euxenite, and samarskite contribute to the observed spot anomalies.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"36 ","pages":"Article 101360"},"PeriodicalIF":3.8,"publicationDate":"2024-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142312000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A new algorithm to determine the spatial coverage of carob (Neltuma piurensis) by ecological floor: Chira-Piura River Basin case","authors":"Cristhian Aldana ,&nbsp;Jaime Lloret ,&nbsp;Wilmer Moncada ,&nbsp;Joel Rojas Acuña ,&nbsp;Yesenia Saavedra ,&nbsp;Vicente Amirpasha Tirado-Kulieva","doi":"10.1016/j.rsase.2024.101363","DOIUrl":"10.1016/j.rsase.2024.101363","url":null,"abstract":"<div><div>The carob tree (<em>Neltuma piurensis</em>) is characteristic of the forests of northern Peru, withstand extreme climatic events such as “El Niño” and droughts, in addition to the influence of climate change, affecting its distribution of coverage at different altitudes. The objective of this article is to propose an algorithm to determine the Spatial Coverage of Carob by Ecological Floor (SCCEF) in the Chira-Piura River Basin, Peru. The method used consisted of measuring the spectral signature of the carob tree with the FieldSpec4 spectroradiometer at three sampling points corresponding to the localities of Cardal, Lancones and Macacará, located on different ecological floors. The comparison of the spectral signatures for Cardal and Lancones gives an R² = 0.9459, for Cardal and Macacará an R² = 0.9866 and for Lancones with Macacará an R² = 0.9469, which allows an accurate identification of the carob tree in the satellite images. The Mann-Whitney-Wilcoxon <em>U</em> test validates the spectral signatures extracted from the satellite images with the spectral signatures measured with the spectroradiometer at Lancones (p-value = 0.9705 &gt;α = 0.05), Cardal (p-value = 0.9819 &gt; 0.05) and Macacará (p-value = 0.7959 &gt; 0.05). The results show that the SCCEF in the Tropical (T) ecological floor represents 1.55 % of the T area, in the Tropical Pre-Montane (TPM) ecological floor it is 1.47 % of the TPM area, in the Low Tropical Montane (LTM) ecological floor it is 0.78 % of the LTM area, in the Montane (M) ecological floor it is 0.69 % of the M area and in the Paramo (P) ecological floor it is 0.35 % of the P area. Therefore, the SCCEF decreases in each ecological floor as its altitude increases.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"36 ","pages":"Article 101363"},"PeriodicalIF":3.8,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142320185","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Data-driven approach for land surface temperature retrieval with machine learning and sentinel-2 data","authors":"Aymen Zegaar ,&nbsp;Abdelmoutia Telli ,&nbsp;Samira Ounoki ,&nbsp;Himan Shahabi ,&nbsp;Francisco Rueda","doi":"10.1016/j.rsase.2024.101357","DOIUrl":"10.1016/j.rsase.2024.101357","url":null,"abstract":"<div><p>This research endeavors to advance land surface temperature (LST) prediction accuracy through the development of a sophisticated machine learning model. Leveraging the potential of Sentinel 2 data and atmospheric parameters, we augment Landsat-based LST with MODIS-based LST, enriching the temporal dimensions of our dataset. A distinctive feature of our study is the pioneering use of Sentinel 2 data as inputs for LST prediction, a facet scarcely explored in the existing literature. Our investigation delves into the correlation dynamics between LST and atmospheric parameters. Notably, the study employs a diverse set of machine learning models, including Extra Trees, Random Forests, LightGBM, XGBoost, and Support Vector Regressor. These models collectively exhibit superior performance, with Extra Trees emerging as a standout performer, with a minimal mean absolute error (MAE) of 0.423, a root mean square error (RMSE) of 1.340 °C, and an impressive coefficient of determination (<span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span>) of 0.984. The exploration of Sentinel 2 data as an input source for LST prediction not only refines predictive accuracy but also opens novel research avenues in the realm of LST dynamics. This study contributes to the existing body of knowledge by introducing innovative methodologies and providing a comprehensive understanding of the intricate correlations influencing LST.</p></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"36 ","pages":"Article 101357"},"PeriodicalIF":3.8,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142271597","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}