Environmental Earth Sciences最新文献

{"title":"Water injection softening modeling of hard roof and application in Buertai coal mine","authors":"Teng Teng,&nbsp;Yulong Chen,&nbsp;Shouguang Wang,&nbsp;Wenjian Jia,&nbsp;Yuming Wang,&nbsp;Kun Liu,&nbsp;Zhaolong Li","doi":"10.1007/s12665-024-12068-1","DOIUrl":"10.1007/s12665-024-12068-1","url":null,"abstract":"<div><p>A hard roof implies a large hanging-roof and high-frequency dynamic strata behavior during mining, which poses a great risk to the safety of personnel and equipment. To solve this problem, a water injection softening method was used in the Buertai coal mine in Inner Mongolia, China, which has a hard sandstone roof. Comprehensive experimental tests and numerical simulations were conducted to investigate the water injection softening effect on the hard roof. Uniaxial tests were conducted on water-softened rock specimens to establish the relationship between the water content and mechanical properties, and the permeability was correlated with the pore water pressure and axial stress. A hydromechanical coupling model was developed and implemented in the numerical model by introducing the water-softening elastic modulus and the dynamic porosity model. Numerical modeling of water injection into the hard roof was conducted to characterize the roof behavior and the dynamic flow field under water injection softening. The results showed that (1) the water weakened the strength and elastic modulus of the rock. As the pore water pressure increased, the permeability increased exponentially. However, with increasing axial stress, the permeability decreased exponentially. (2) The Terzaghi effective stress principle and static equilibrium equation were combined to derive the Biot three-dimensional consolidation control equation with the strain tensor and pore water pressure, which can effectively describe the coupling relationship between the pore water flow and the elastic deformation of the elastic body of a porous medium. Expressions for the porosity of the elastic body of the porous medium were determined. Porosity was expressed as a function of the Biot coefficient, volumetric strain, pore water pressure, and bulk modulus, which made the model more comprehensive and reasonable. (3) The pore water pressure, strain, and permeability were higher near the water injection hole. The respective increases in pore water pressure, strain, and permeability were rapid at the beginning and diminished with subsequent water injection.</p></div>","PeriodicalId":542,"journal":{"name":"Environmental Earth Sciences","volume":"84 2","pages":""},"PeriodicalIF":2.8,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hydrogeochemical study at a reforestation area from Itu city, São Paulo State, Brazil","authors":"Isabella G. Lee,&nbsp;Daniel M. Bonotto","doi":"10.1007/s12665-024-12081-4","DOIUrl":"10.1007/s12665-024-12081-4","url":null,"abstract":"&lt;div&gt;&lt;p&gt;The Itu city at São Paulo State, Brazil, has a significant dependence on surface waters availability, facing difficulties for their supply over the last years due to the accentuated population growth in the region. Thus, the demand for groundwater use raised there what is specifically true for the Forest Experiment Center, managed by the NGO SOS Atlantic Forest and located within the Water Resources Management Unit (UGRHI) 10—Sorocaba and Médio Tietê. Nowadays, there is incipient hydrogeochemical knowledge of those groundwater resources and, in addition to the area having suffered a severe water crisis, the water quality of the surface waters of this region is poor to regular, according to some reports, as a consequence of the activities developed there. Therefore, this study focused that site, aiming to get a better understanding of the hydrogeochemical processes occuring there and their implications for water quality, once the urban growth usually results in changes in the hydrologic cycle with possible pollutants releases. Physicochemical parameters and inorganic compounds of the waters were analyzed in order to identify possible anomalous concentrations of contaminants, especially those related to agricultural activities such as nitrogen and phosphate fertilizers, since the area was used for agriculture before reforestation. The radionuclides radon (&lt;sup&gt;222&lt;/sup&gt;Rn) and radium (&lt;sup&gt;226&lt;/sup&gt;Ra) were also analyzed as the study area is located near the Botuxim deposit, a low-level nuclear waste disposal site that may be a possible source of contamination. Additional motivation for characterizing radon in the study area consisted on its use as a natural tracer to understand hydrogeological processes, as well as by its great risk to human health. This work has taken into account the results obtained during one monitoring campaign held for the following sampling: (1) nine tubular wells drilled at Tubarão Aquifer System; (2) one surface water from a dam (reservoir) built in the area; (3) rainwater. Results show that groundwater samples are generally alkaline, with pH values between 6.24 and 8.51, and total dissolved solids (TDS) ranging from 67.22 to 119.17 mg/L. Those waters are slightly oxidizing, with Eh values between + 188 to + 284 mV. Most of groundwaters are sodium-bicarbonate dominated, except two samples that are mixed in terms of dissolved anions. The dam (reservoir) water and rainwater are mixed in terms of dissolved cations, but dominated by chloride (dam water) or bicarbonate (rainwater). The phosphate levels exceeded the Brazilian standards for human consumption in some samples, which is probably associated with the ancient agricultural activities of the region, because the aquifer’s rocks are not naturally enriched in PO&lt;sub&gt;4&lt;/sub&gt;&lt;sup&gt;3−&lt;/sup&gt;. &lt;sup&gt;222&lt;/sup&gt;Rn activity concentration reached a maximum value of 32.8 Bq/L, below of the previous WHO's recommended limit of 100 Bq/L, while the highest &lt;sup&gt;226&lt;/sup&gt;Ra activity","PeriodicalId":542,"journal":{"name":"Environmental Earth Sciences","volume":"84 2","pages":""},"PeriodicalIF":2.8,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938942","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intercomparison of sediment transport curve and novel deep learning techniques in simulating sediment transport in the Wadi Mina Basin, Algeria","authors":"Mohammed Achite,&nbsp;Okan Mert Katipoğlu,&nbsp;Nehal Elshaboury,&nbsp;Türker Tuğrul,&nbsp;Kusum Pandey","doi":"10.1007/s12665-024-12051-w","DOIUrl":"10.1007/s12665-024-12051-w","url":null,"abstract":"<div><p>The accurate estimation of sediment discharge is crucial for the design and operation of engineering structures such as dams, water treatment facilities, and erosion control systems. This study evaluates the performance of various machine learning (ML) and deep learning (DL) models in predicting sediment transport in the Mina Basin, Algeria, at two stations: Oued Abtal and Sidi Abdelkader Djillali. The models include the sediment rating curve, category boosting, convolutional neural network, deep neural network (DNN), gated recurrent unit, and multilayer perceptron. Among these, the DNN model consistently demonstrated superior performance. For Oued Abtal station, the DNN achieved RMSE = 243.72 kg/s, MAE = 102.17 kg/s, NSE = 0.99, and PBIAS = 6.81%. At Sidi Abdelkader Djillali station, it recorded RMSE = 91.27 kg/s, MAE = 46.51 kg/s, NSE = 0.99, and PBIAS = 38.06%. Error analysis revealed that the DNN model offers the most reliable predictions, outperforming both traditional and other ML/DL methods. This study underscores the potential of deep learning models in advancing sediment transport prediction, particularly in semi-arid regions, and highlights their implications for sustainable water resource management.</p></div>","PeriodicalId":542,"journal":{"name":"Environmental Earth Sciences","volume":"84 2","pages":""},"PeriodicalIF":2.8,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938705","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Geochemical characterization of potentially toxic elements in topsoil under different land-use patterns in the village of Guido (Midwestern Burkina Faso) using multivariate geostatistical techniques","authors":"Michel Bembamba,&nbsp;Aboubakar Sako","doi":"10.1007/s12665-024-12050-x","DOIUrl":"10.1007/s12665-024-12050-x","url":null,"abstract":"<div><p>Burkina Faso faces a major challenge of environmental degradation due to a booming of gold mining. To date, there is no available information regarding soil geochemical status of this rapidly transitioning land use from merely subsistence agriculture to market gardening and artisanal gold mining. Therefore, this case study investigates distribution of 13 potentially toxic elements in soil exposed to different land-uses. For that purpose, 226 topsoil samples were collected in a grid of 200 m × 200 m, and their pseudototal concentrations were determined by inductively coupled plasma mass spectrometer. Univariate statistics, multivariate and geostatistical techniques showed that chemical weathering of parent bedrocks contributed to La, Tl, Th, U and Ti distribution in the soil, whereas that of Au, Hg and Te were controlled by artisanal gold mining. Laterization of basaltic rocks appeared to be the main source of V, Ga and Sc. In contrast, spatial distribution of Sr and Ba might be attributed to application of inorganic fertilizers and agrochemicals and, to lesser degree, parent materials. The results of multivariate analyses were corroborated by the interpolated factor score maps. The high concentrations of V, Sc, Bi, Hg and Sb above the mean upper continental crust composition and world-average soil concentrations are likely to pose serious threats to human. The study showed that the soil geochemistry is affected by both geogenic and anthropogenic sources. Thus, understanding geochemical status of the soil is vital for developing sustainable agricultural practices and environmental protection schemes in the area.</p></div>","PeriodicalId":542,"journal":{"name":"Environmental Earth Sciences","volume":"84 2","pages":""},"PeriodicalIF":2.8,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Seismic landslide risk assessment based on landslide density optimized Newmark model: new insights from the Xianshuihe fault zone in the Eastern Tibetan Plateau, China","authors":"Caihong Li,&nbsp;Changbao Guo,&nbsp;Xujiao Zhang,&nbsp;Xue Li,&nbsp;Yiqiu Yan","doi":"10.1007/s12665-024-12056-5","DOIUrl":"10.1007/s12665-024-12056-5","url":null,"abstract":"<div><p>The potential hazard of seismic landslides is notably high within active fault zones, currently, the commonly used Newmark model for seismic landslide risk assessment often predicts cumulative displacement that are lower than the actual displacement, In order to enhance the earthquake landslide risk assessment accuracy, a new LS-D-Newmark (Landslide density Newmark) model, which considers the attenuation of geotechnical mechanical parameters in areas with different historical landslide densities, is proposed to evaluate the potential seismic landslide hazard. The Xianshuihe fault zone in the eastern Tibetan Plateau was selected as an example, a historical landslide database was established based on fault activity, field investigation, multi-source remote sensing and InSAR monitoring. The landslide hazards in the Xianshuihe fault zone are distributed linearly along the fault zone and are more concentrated at the intersection of the faults. The results of potential seismic landslide risk assessment based on LS-D-Newmark model show that its prediction accuracy (<i>AUC</i> value) increased from 0.78 to 0.84, a 7.69% improvement compared to the traditional Newmark model. Using the spatial characteristics of landslides triggered by the 2022 Luding Ms 6.8 earthquake for verification, and it was found that 75.87% of the landslides were located in the extremely high risk areas and high risk areas predicted by the LS-D-Newmark model, which is consistent with the actual distribution of landslides. The proposed LS-D-Newmark model effectively resolves the issue of underestimating displacement predictions, enhancing the accuracy of potential seismic landslide risk assessments, and provides an important reference for major project planning and construction as well as disaster prevention and mitigation in the region.</p></div>","PeriodicalId":542,"journal":{"name":"Environmental Earth Sciences","volume":"84 2","pages":""},"PeriodicalIF":2.8,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"High-altitude deformation and reactivation mechanism of large ancient landslides along the Shadingmai section of the upper Jinsha River, Tibetan Plateau","authors":"Changbao Guo,&nbsp;Zhendong Qiu,&nbsp;Ruian Wu,&nbsp;Yanan Zhang,&nbsp;Yiqiu Yan,&nbsp;Wenkai Chen,&nbsp;Peng Wei,&nbsp;Jixin Liu","doi":"10.1007/s12665-024-12053-8","DOIUrl":"10.1007/s12665-024-12053-8","url":null,"abstract":"<div><p>The high-altitude creeping-deformation of large ancient landslides represents a distinctive pattern resulting from the intricate geomorphological and geological evolution along the eastern Tibetan Plateau. The deformation initiates a cascade of hazardous events, including sliding, river blockage, and dam failure. Studying the high-altitude deformation mechanisms of ancient landslides in alpine canyon areas presents formidable challenges. This study narrows its focus to the Shadingmai section in the upper Jinsha River, employing remote sensing interpretation, field investigations, InSAR deformation monitoring, and statistical analysis of regional rainfall data. The development, distribution, and deformation characteristics of high-altitude landslides were investigated. The findings reveal that 30 typical landslides within the study area, which are influenced by regional stratigraphic rock mass structures and lithological characteristics. Notably, InSAR deformation monitoring records a maximum deformation rate of -30 mm/a in the landslides, predominantly exhibiting characteristics of high-altitude deformation. The Shadingmai ancient landslide epitomizes a typical high-altitude landslide, with surface deformations predominantly characterized by tensile cracks, fissures in buildings, scraps, and localized sliding. Drawing upon SBAS-InSAR technology monitoring and regional rainfall data analysis, the result discerns the hysteresis effect and the “step-like” growth pattern in the cumulative deformation of the Shadingmai ancient landslide. In deeply incised canyon areas, large ancient landslides with high-position thrust-type deformation are complex and highly prone to triggering a disaster chain under heavy rainfall, involving high-position shear failure, landslide damming of rivers, and subsequent dam-break flooding. Ultimately, the results of this study furnish a fundamental theoretical basis crucial for preemptive measures aimed at averting large-scale geological disasters in the upper Jinsha River.</p></div>","PeriodicalId":542,"journal":{"name":"Environmental Earth Sciences","volume":"84 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142912943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Vulnerability reduction in post-conflict areas through the Resource Nexus approach (Water–Soil-Food-Atmosphere) to sustainable food production systems: a case study in Colombia","authors":"Serena Caucci,&nbsp;Jairo Guzman-Molina,&nbsp;Abdulhakeem Al-Qubati,&nbsp;Marie Schellens","doi":"10.1007/s12665-024-12018-x","DOIUrl":"10.1007/s12665-024-12018-x","url":null,"abstract":"<div><p>The prolonged armed conflict in Colombia, spanning over the last five decades, has significantly impacted its agricultural areas and led to the widespread displacement and disruption of farming activities. The agricultural sector is crucial for Colombia as it contributes to food security, the economy, and the Nation’s employment rate. However, the agricultural sector is challenged by the environment and its natural resources, especially water in water abstraction and soil in terms of degradation and land cover change. Additionally, climate change exacerbates these challenges by altering precipitation patterns, increasing the frequency of extreme weather events, and further stressing water and soil resources, making sustainable management even more critical. The Resource Nexus approach comes into play to cope with and mitigate such challenges. Combined with social equity to advance the sustainability of agriculture, the Nexus approach demonstrates pathways towards the achievement of the Sustainable Development Goal (SDG) 2 (Zero Hunger)in synergies with other SDGs, like SDG 5 (Gender Equality), SDG 6 (Clean Water and Sanitation), SDG 10 (Reduced Inequality), SDG 12 (Responsible Consumption and Production), SDG 13 (Climate Action), and SDG 15 (Life on Land). This paper addresses the dual challenge of improving natural resources management and population vulnerability reduction in the frame of environmental conflicts and population inequalities that severely affect the resilience of food systems. In line with principles of inclusion and gender equity, the methodology developed here aims to identify Colombia's productive regions that would benefit from enhanced management at the landscape level, the Resource Nexus approach. With the use of geographic information systems (GIS), this research spatially evaluates the (i) impact of land-use changes and the land-use fragmentation due to resource overuse, (ii) the provision of ecosystem services under different uses of natural resources and suggests ecosystem services planning as a methodology for municipal ecosystem-based management, (iii) climate change and the anthropogenic impacts on agricultural productivity in Colombia at the municipality scale. The results indicate significant environmental changes over the past few decades, including reduced natural forests and increased agricultural land. This shift has coincided with a decrease in freshwater availability. Additionally, there is a concerning trend of agricultural expansion into protected areas, highlighting the ongoing pressures on natural resources and the need for sustainable management practices. This study underscores the value of the science-policy interface to ensure increased social equity, economic growth, and resource conservation.</p></div>","PeriodicalId":542,"journal":{"name":"Environmental Earth Sciences","volume":"84 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s12665-024-12018-x.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142912955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Periodic variations of karstic spring discharge and precipitation from the perspective of wavelet analysis techniques: a case study of tacin spring (Kayseri, Türkiye)","authors":"Murat Çeliker,&nbsp;Selman Uzun,&nbsp;Güngör Yıldırım","doi":"10.1007/s12665-024-12029-8","DOIUrl":"10.1007/s12665-024-12029-8","url":null,"abstract":"<div><p>Global climate change is just one of the pressures which water resources and their management will face in the upcoming years. To evaluate the impacts of climatic pressure on Tacin karstic spring in water management, this research aims to understand between the role of precipitation on the spring discharge using wavelet analysis techniques. Here, advanced wavelet analysis techniques such as Continuous Wavelet Transform (CWT), Cross Wavelet Transform (XWT), Wavelet Power Spectrum (WPS) and Wavelet Transform Coherence (WTC) were used. This research is the first application of these wavelet techniques in the region and provides new insights into the hydrological dynamics of the karstic system. In addition to Principal Component Analysis (PCA) and Thiessen Polygon Method (TPM), which have been used in many studies in the literature to identify the dominant patterns of variability in multiple rainfall time series, we also used dimensionality reduction techniques such as the Median-Based Reduction (MBR) method, which we introduced to the literature for the first time in this study. In this study, we leveraged 57 years of concurrent monthly data covering precipitation and spring discharge across Kayseri, Pınarbaşı, Gemerek, and Şarkkışla (1965–2022). The results show that the karstic spring discharge (2–6-year scale, 7–10-year scale, 10–15-year scale, 15–24-year scale and 25–30-year scale) and precipitation (3–6-year scale, 5–12-year scale, 13–21-year scale and 21–30-year scale) all have multi-year periodic variations, which might be controlled by climate. During the short-term interval, precipitation exhibited variations occurring over a span of 9–15 months, while the discharge rate demonstrated changes on a scale of 8–16 months. The hydraulic response time of the spring to precipitation is nearly at 78–82 days. Based on the findings of the analysis, it can be inferred that the distinct periods and time series of precipitation and discharge correlate with the heterogeneous structure of the karstic spring and the reservoir volume.</p></div>","PeriodicalId":542,"journal":{"name":"Environmental Earth Sciences","volume":"84 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142912872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative assessment of microplastic pollution in Terekhol and Sal estuaries, Goa, India","authors":"Niyati Kalangutkar,&nbsp;Shritesh Mhapsekar,&nbsp;Parvathy Rajagopal","doi":"10.1007/s12665-024-12042-x","DOIUrl":"10.1007/s12665-024-12042-x","url":null,"abstract":"<div><p>Global concern regarding microplastics (MPs) has increased due to their potential risks. The primary source of microplastic contamination in the ocean is often terrestrial transfer from nearby locations. This study evaluated microplastic pollution in the Terekhol and Sal estuaries, found near their mouths, during the monsoon season of 2022. The size, shape, and colour of the MPs were determined using stereomicroscope, while Fourier-transform infrared (FTIR) analysis was used for polymer identification. The average concentration of MPs in the Terekhol and Sal estuaries were 0.25 particles/L and 0.30 particles/L, respectively, with the highest concentrations detected in the 5 –1 mm size range in both estuaries. While fibres predominated in the Terekhol estuary and fragments were more common in the Sal estuary, white was the dominating colour in both estuaries. Polymer identification revealed the presence of polyethylene (PE), polypropylene (PP), and polyamide in both estuaries. The Pollution Load Index (PLI) values exceeded 1 indicated that both estuaries are contaminated with MPs. Scanning electron microscopy (SEM) and energy dispersive X-ray spectroscopy (EDS) analysis of MPs from both estuaries indicated varying levels of surface degradation and also the presence of various elements (C, O, Fe, Si, Ru, Cu, Co, Zn, Al, K, Na and Cl) on the surface of these MPs. These findings suggest that river inflows and fishing-related activities are likely the primary contributors to pollution caused by MPs in these estuaries.</p></div>","PeriodicalId":542,"journal":{"name":"Environmental Earth Sciences","volume":"84 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142912868","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Forecasting land use in urban Himalayas: a remote sensing-guided machine learning approach","authors":"Sadaf Fayaz,&nbsp;Akhlaq Amin Wani,&nbsp;Aasif Ali Gatoo,&nbsp;MA Islam,&nbsp;Shah Murtaza,&nbsp;Khursheed Ahmad Sofi,&nbsp;Parvez Ahmad Khan","doi":"10.1007/s12665-024-12060-9","DOIUrl":"10.1007/s12665-024-12060-9","url":null,"abstract":"<div><p>Rapid urbanization in the Himalayan region due to advances in transportation, tourism and industry impacts natural resources causing its depletion. The problem gets aggravated in the urban regions located in the eco-fragile Himalayas. Srinagar being one of the largest urban hubs in the region with exceptionally high population growth rate, the complexities in monitoring land use and associated changes due to conventional methods further exacerbates these issues. Rapid and accurate mapping of land use land cover (LULC) is essentially required for effective green space management in urban landscapes. In this study an assessment of LULC using machine learning based classifiers was done. The present study assessed LULC using Sentinel-2 data through unsupervised K-means algorithm and supervised machine learning algorithms (Artificial Neural Network-ANN, Support Vector Machine- SVM, Random Forest-RF and Decision Tree-DT). Ground truth points collected through extensive field visits and high resolution Google Earth Pro were used for model generation/mapping (70%) and validation (30%). Map validation revealed that SVM (96.60%) had the highest overall accuracy followed by RF (95.86%), DT (95.33%), ANN (88.7%) and K-means (64.51%). F-Scores varied between classifiers on account of precision and recall for different classes. High values for F depicting performance of classification models were observed for all supervised classifiers except ANN which couldn’t effectively classify wastelands (F = 58.73%), SVM performed exceptionally well for agriculture and grassland (94.02%), Habitation (96.02%) and wasteland (96.42%). DT excelled in mapping vegetation (99.41%). Waterbody was classified accurately by all the classifiers (F = 100%) except ANN (99.73%). However, Snow and Agriculture Fallow were depicted well by ANN with F Score of 99.20% and 96.39% respectively.</p></div>","PeriodicalId":542,"journal":{"name":"Environmental Earth Sciences","volume":"84 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142912871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}