Physics and Chemistry of the Earth最新文献_第5页

Performance assessment of irrigated sugarcane using remote sensing: A case study of Kasinthula cane growers limited, Malawi 利用遥感技术对灌溉甘蔗进行绩效评估：以马拉维Kasinthula甘蔗种植者有限公司为例

IF 4.1 3区地球科学

Physics and Chemistry of the Earth Pub Date : 2025-08-29 DOI: 10.1016/j.pce.2025.104094

Daniel Sambakunsi , Grivin Chipula , Lameck Fiwa , Chikondi Makwiza , Patsani Kumambala , Mwabuke Nkhata

{"title":"Performance assessment of irrigated sugarcane using remote sensing: A case study of Kasinthula cane growers limited, Malawi","authors":"Daniel Sambakunsi , Grivin Chipula , Lameck Fiwa , Chikondi Makwiza , Patsani Kumambala , Mwabuke Nkhata","doi":"10.1016/j.pce.2025.104094","DOIUrl":"10.1016/j.pce.2025.104094","url":null,"abstract":"<div><div>Assessing irrigated sugarcane performance accurately and in a timely manner is crucial for optimizing productivity. This is especially important for ensuring sustainable water use in agriculture and maintaining food and water security in semi-arid regions that are increasingly impacted by climate variability. This study leveraged remote sensing technologies to evaluate the performance of irrigated sugarcane at Kasinthula Cane Growers Limited (KCGL) in Malawi. It specifically applied the PySEBAL to Landsat 8 imagery. The results were validated using FAO's WaPOR datasets. The validated results for PySEBAL and WaPOR were compared to the FAO Penman-Monteith equation. The FAO Penman-Monteith equation uses meteorological to calculate reference evapotranspiration. Key performance indicators (KPIs) like actual evapotranspiration (AET), biomass production, adequacy, equity, and uniformity were analyzed for the 2019 and 2020 seasons. PySEBAL-derived AET showed strong agreement with FAO Penman-Monteith estimates and WaPOR data (R<sup>2</sup> = 0.83 in 2019; 0.78 in 2020; RMSE = 42.1 mm and 23.8 mm, respectively). Biomass estimates correlated with observed sugarcane yields (R<sup>2</sup> = 0.74 in 2019; 0.68 in 2020). Centre-pivot irrigation exhibited higher uniformity, while furrow systems demonstrated greater equity. As the first study to compare PySEBAL and WaPOR in a Malawian sugarcane estate, the findings underscore the potential of remote sensing for evidence-based irrigation and water management in data-scarce regions. This study used a combined approach of Penman-Monteith, PySEBAL, and WaPOR to comprehensively evaluate irrigation performance at KCGL. This integrated approach can effectively support operational decisions and enhance water productivity in large-scale sugarcane systems, especially in data-scarce regions.</div></div>","PeriodicalId":54616,"journal":{"name":"Physics and Chemistry of the Earth","volume":"141 ","pages":"Article 104094"},"PeriodicalIF":4.1,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145019306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A mathematical modelling-based interpretable deep learning approach for lettuce disease detection in extreme environmental conditions 一种基于数学模型的可解释深度学习方法，用于极端环境条件下的生菜病害检测

IF 4.1 3区地球科学

Physics and Chemistry of the Earth Pub Date : 2025-08-29 DOI: 10.1016/j.pce.2025.104080

Ajit Singh Rathor , Sushabhan Choudhury , Abhinav Sharma , Gautam Shah , Pankaj Nautiyal

{"title":"A mathematical modelling-based interpretable deep learning approach for lettuce disease detection in extreme environmental conditions","authors":"Ajit Singh Rathor , Sushabhan Choudhury , Abhinav Sharma , Gautam Shah , Pankaj Nautiyal","doi":"10.1016/j.pce.2025.104080","DOIUrl":"10.1016/j.pce.2025.104080","url":null,"abstract":"<div><div>Lettuce is a widely consumed crop with significant nutritional value. However, leaf diseases in the lettuce can degrade plant health, diminish plant yield, and lead to substantial economic losses. Therefore, detection of these diseases at early stage is extremely vital. To address the challenge of disease identification in real-world field conditions, we introduce a multi-level feature extraction framework, CNN-WOPNet. This study utilized a lettuce NPK dataset cultivated under extreme environmental conditions in a hydroponics system. The proposed model utilizes a mathematical Walrus Optimization algorithm for CNN hyperparameter tuning, and a parallel network (ParNet) attention module to develop a novel classification network (CNN-WOPNet). This network processes the multi-level deep features from the optimized CNN and attention module, effectively emphasizing crucial locations in plant disease images. CNN-WOPNet model classified diverse range of plant diseases with an impressive performance metrics such as accuracy 99.54 %, precision 99.60 %, F1-score 99.61 %, and recall 99.61 %. ParNet module demonstrated the shortest training and testing times, 755.82 s and 0.01 s, respectively, while delivering competitive performance compared to existing methods. An ablation study was also conducted, demonstrating the efficacy of proposed model.</div></div>","PeriodicalId":54616,"journal":{"name":"Physics and Chemistry of the Earth","volume":"141 ","pages":"Article 104080"},"PeriodicalIF":4.1,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145019307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Factors affecting ecosystem services varied in space in Pearl River Delta, China 珠江三角洲生态系统服务功能的影响因子在空间上存在差异

IF 4.1 3区地球科学

Physics and Chemistry of the Earth Pub Date : 2025-08-29 DOI: 10.1016/j.pce.2025.104071

Ayinuer Yushanjiang , Weiqi Zhou , Jiali Wang , Jing Wang

{"title":"Factors affecting ecosystem services varied in space in Pearl River Delta, China","authors":"Ayinuer Yushanjiang , Weiqi Zhou , Jiali Wang , Jing Wang","doi":"10.1016/j.pce.2025.104071","DOIUrl":"10.1016/j.pce.2025.104071","url":null,"abstract":"<div><div>Ecosystem services (ESs) have undergone substantial changes as a result of human and natural interventions, particularly within urban megaregions. A multitude of studies have investigated the spatial-temporal dynamics of ESs and their driving factors. However, these researches have largely focused on the negative impacts of factors on ESs, with less attention given to the positive contributions of both natural and human factors. To fill this gap, this study quantified ESs with the spatial-temporal dynamics in the Pearl River Delta (PRD) and further explored the impacts of social and natural drivers and how such impacts varied in space. The result showed a 35.54 % and 11.62 % decrease in food production (FP) and carbon sequestration and oxygen production (COSP), respectively, but an 11.07 % and 28.86 % increase in water retention (WR) and soil conservation (SC). The changes in ESs in highly developed central cities are mainly affected by gross domestic production (GDP) and population (POP). In contrast, the ESs in the periphery of the PRD with relatively low development density were mainly affected by natural factors. It is worth noting that while human activities caused the loss of ESs in some regions, there are regions where GDP and POP had positive impacts on ESs. These results underscore the importance of place-based strategies to mitigate the adverse impacts on ESs.</div></div>","PeriodicalId":54616,"journal":{"name":"Physics and Chemistry of the Earth","volume":"141 ","pages":"Article 104071"},"PeriodicalIF":4.1,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144926029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Microstructural and mechanical behavior of conglomerate in interbedded rock slopes: Insights into microscopic complexity and fracture mechanism 岩质互层边坡中砾岩的微观结构和力学行为：对微观复杂性和断裂机制的认识

IF 4.1 3区地球科学

Physics and Chemistry of the Earth Pub Date : 2025-08-28 DOI: 10.1016/j.pce.2025.104066

Mohd Mustaqim Mohd-Nordin , Mohd Ashraf Mohamad Ismail , Hamzah Hussin

{"title":"Microstructural and mechanical behavior of conglomerate in interbedded rock slopes: Insights into microscopic complexity and fracture mechanism","authors":"Mohd Mustaqim Mohd-Nordin , Mohd Ashraf Mohamad Ismail , Hamzah Hussin","doi":"10.1016/j.pce.2025.104066","DOIUrl":"10.1016/j.pce.2025.104066","url":null,"abstract":"<div><div>The microstructural and mechanical behavior of conglomerate rock in interbedded sedimentary slopes is critically influenced by intrinsic heterogeneity, including varied clast sizes, weak cementation, and discontinuous matrix fabrics that form mechanically weak zones. This study integrates mineralogical, microstructural, and mechanical analyses to investigate degradation behavior and its implications for slope stability. Petrographic and SEM-EDS analyses reveal that mineralogical variation, particularly the kaolinite/muscovite ratio, concentrates stress at clast-matrix interfaces, promoting fracture initiation. X-ray micro-CT imaging and pore network modeling expose internal fabric irregularities, grain clustering, and potential fracture pathways. Cyclic wetting and drying induce microstructural deterioration, with the wet–dry deviation of unit weight increasing from 1.15 % to 1.87 %, accompanied by stiffness loss and increased brittleness. Shear and elastic moduli increase on average by 69.6 % and 22.5 %, respectively, indicating evolving mechanical behavior. Finite element analysis confirms that reduced stiffness lowers the critical Strength Reduction Factor (SRF) by 8.5 %, compromising slope stability. A 5 % decline in the shear-to-elastic modulus ratio (G/E) and a reduced Poisson's ratio further reflect microcrack propagation and mineral alteration. Connected porosity increases by 15.9 %, indicating the development of fracture connectivity. The estimated Joint Roughness Coefficient (JRC), ranging from 12 to 14 via X-ray micro-CT, aligns with naturally generated fractures, validating surface roughness characteristics. These multi-scale results offer mechanistic insights into the weakening behavior of conglomerates, improving durability assessments and enhancing the reliability of geomechanical models for slope stability prediction in interbedded sedimentary environments.</div></div>","PeriodicalId":54616,"journal":{"name":"Physics and Chemistry of the Earth","volume":"141 ","pages":"Article 104066"},"PeriodicalIF":4.1,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144988874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Forensic investigation of a failed overburden dump: A case study of an opencast mine site in central India 失效覆岩堆的法医调查：印度中部露天矿场的案例研究

IF 4.1 3区地球科学

Physics and Chemistry of the Earth Pub Date : 2025-08-28 DOI: 10.1016/j.pce.2025.104091

Rahul Shende , Srinivasan V. , Anjan Patel , Ajay Chhangani , Jagdish Gouda

{"title":"Forensic investigation of a failed overburden dump: A case study of an opencast mine site in central India","authors":"Rahul Shende , Srinivasan V. , Anjan Patel , Ajay Chhangani , Jagdish Gouda","doi":"10.1016/j.pce.2025.104091","DOIUrl":"10.1016/j.pce.2025.104091","url":null,"abstract":"<div><div>Instability of external overburden (OB) dumps poses a major geotechnical and operational challenge in opencast coal mines, often leading to deformation, sliding, and loss of dumping capacity. This paper presents a distinctive forensic investigation conducted in central India, focusing on external overburden dump instability. The site exhibited significant signs of failure, including excessive ground heaving near the dump boundary, mass sliding of the OB, and the formation of large peripheral cracks. A detailed subsurface exploration was carried out through borehole investigations across two external OB dumps to assess their stratification. Variations in stratigraphy, combined with comprehensive macro- and micro-scale laboratory analyses, provided critical insights into the mechanisms contributing to dump failure. The study highlights the influence of weak foundation soils and stratigraphic variability on dump performance. Moreover, it proposes an effective remedial approach to mitigate ongoing deformation, stabilize the pre-existing OB dump, and enhance its dumping capacity. The methodology outlined offers a strategic framework for assessing and managing OB dump failures over weak subsoil conditions.</div></div>","PeriodicalId":54616,"journal":{"name":"Physics and Chemistry of the Earth","volume":"141 ","pages":"Article 104091"},"PeriodicalIF":4.1,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144918034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Spatiotemporal characteristics of carbon storage in mangrove communities at different restoration stages and its influencing factors in Hainan Province 海南红树林群落不同恢复阶段碳储量时空特征及其影响因素

IF 4.1 3区地球科学

Physics and Chemistry of the Earth Pub Date : 2025-08-28 DOI: 10.1016/j.pce.2025.104079

Youwei Lin , Ruina Liu , Yunfeng Shi , Huaibao Zhao , Zongbo Peng , Shengjie Han

{"title":"Spatiotemporal characteristics of carbon storage in mangrove communities at different restoration stages and its influencing factors in Hainan Province","authors":"Youwei Lin , Ruina Liu , Yunfeng Shi , Huaibao Zhao , Zongbo Peng , Shengjie Han","doi":"10.1016/j.pce.2025.104079","DOIUrl":"10.1016/j.pce.2025.104079","url":null,"abstract":"<div><div>The mangrove ecosystem is notable for its high carbon storage capacity and strong carbon sequestration potential. Optimizing carbon storage requires selecting mangrove species with high carbon density and ideal carbon sink environments. This study investigates coastal mangroves restored near the Tielu Port Mangrove Protection Area in Sanya, Hainan Province, by comparing carbon storage across mangrove communities of different ages, tidal elevations, and planting patterns. The aim is to understand the impact of various biological and environmental factors on mangrove carbon storage. Carbon storage in this study includes both plant and soil carbon storage. Plant carbon storage is estimated by measuring the biomass of above-ground and below-ground vegetation, as well as litter, while soil carbon storage is calculated by determining soil organic carbon. Results indicate that mangrove carbon storage typically increases with tree age, primarily due to the continuous accumulation of soil carbon. Additionally, mangroves at higher tidal elevations exhibit greater carbon storage compared to those at lower elevations. There is an interaction between tidal elevation and species, with tidal elevation influencing different species to varying extents. For 10-year-old mangrove and repaired communities in the study area, the carbon storage hierarchy is as follows: <em>Sonneratia apetala > Avicennia corniculatum > Avicennia corniculatum</em> + <em>Laguncularia racemosa</em> > <em>Sonneratia apetala</em> > <em>Avicennia marina > Laguncularia racemosa</em>, with respective carbon storage values of 305.52, 236.26, 178.15, 172.96, 145.99, 136.98, and 97.42 t hm<sup>−2</sup>. This research provides a scientific basis for formulating effective mangrove carbon sink afforestation strategies.</div></div>","PeriodicalId":54616,"journal":{"name":"Physics and Chemistry of the Earth","volume":"141 ","pages":"Article 104079"},"PeriodicalIF":4.1,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145004566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Provenance assessment, transport mechanisms, and human health threats of trace elements in the water resources of Northern Coalfield Limited, Central India 印度中部北部煤田有限公司水资源中微量元素的来源评估、运输机制和人类健康威胁

IF 4.1 3区地球科学

Physics and Chemistry of the Earth Pub Date : 2025-08-28 DOI: 10.1016/j.pce.2025.104092

Abhinesh Kumar Singh , Rajesh Singh , Shive Prakash Rai , Sury Kant Singh , Raju Rai , Abhinav Patel , Dev Sen Gupta , U. Saravana Kumar , Nijesh Puthiyottil , Jacob Noble

{"title":"Provenance assessment, transport mechanisms, and human health threats of trace elements in the water resources of Northern Coalfield Limited, Central India","authors":"Abhinesh Kumar Singh , Rajesh Singh , Shive Prakash Rai , Sury Kant Singh , Raju Rai , Abhinav Patel , Dev Sen Gupta , U. Saravana Kumar , Nijesh Puthiyottil , Jacob Noble","doi":"10.1016/j.pce.2025.104092","DOIUrl":"10.1016/j.pce.2025.104092","url":null,"abstract":"<div><div>The water resources in Northern Coalfield Limited (NCL), Singrauli, are liable to dynamic changes due to continued mining activities. To understand how mining activities at NCL affect the chemical makeup of ground and surface water, this study analyzed water samples from both sources to determine the movement of ions. The results of chemometric and classical bivariate analysis projects the mechanism behind the groundwater and surface water chemistry. The chemometric and geospatial result confirms silicate weathering as the governing factor, nitrate contamination as anthropogenically sourced, while fluoride is attributed to both natural and anthropogenic sources. Based on the heavy metal pollution index, both groundwater (60 %) and surface water (57 %) in the open-cast coal mining area of Central India are unsuitable for drinking. Groundwater samples showed contamination with nitrate, fluoride, aluminum, chromium, copper, iron, lead, manganese, mercury, cadmium, and nickel. Notably, high Chronic Daily Intake (CDI<sub>oral</sub>) and Hazard Quotient (HQ) values for aluminum and manganese in both water sources further confirm their unsuitability for any use. This multi-approach study provides new insights into how mining activities influence the chemistry of groundwater and surface water. Assessing the condition of water resources in this region is crucial for creating effective and sustainable management strategies applicable here and in similar areas.</div></div>","PeriodicalId":54616,"journal":{"name":"Physics and Chemistry of the Earth","volume":"141 ","pages":"Article 104092"},"PeriodicalIF":4.1,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144988872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exploring the early lifecycle risk factors – Project dimensions – Resilience nexus in water infrastructure projects in small island developing states 探索早期生命周期风险因素-项目维度-小岛屿发展中国家水利基础设施项目的复原力联系

IF 4.1 3区地球科学

Physics and Chemistry of the Earth Pub Date : 2025-08-27 DOI: 10.1016/j.pce.2025.104075

Zaheer Doomah, Sharmeen Jahmeerbacus

{"title":"Exploring the early lifecycle risk factors – Project dimensions – Resilience nexus in water infrastructure projects in small island developing states","authors":"Zaheer Doomah, Sharmeen Jahmeerbacus","doi":"10.1016/j.pce.2025.104075","DOIUrl":"10.1016/j.pce.2025.104075","url":null,"abstract":"<div><div>The combined effects of rapid urbanisation, increased population and climate change are putting an increasing stress on the water sector globally. Although the early lifecycle stages (ELS) of water infrastructure projects provide significant scope for improving resilience to achieve SDG targets, these phases are also fraught with various risks that can have severe consequences. However, there is still a paucity of research on the impacts of risks on key project management dimensions and ultimately resilience, especially in Small Island Developing States (SIDS). This study thus aims to bridge this research gap by identifying risk factors and their associated impacts at the planning, design and procurement phases before developing a resilience framework applicable to ELS of water sector projects in SIDS. A qualitative approach using semi-structured interviews with a purposive sample of fourteen (14) project professionals was adopted. Thematic analysis was then used to identify seventeen important risk factors affecting the resilience dimensions of water infrastructure in the ELS. The three most prevalent risks were late clearances from authorities, inadequate design for climate change and lack of experienced local contractors for the planning, design and procurement phases respectively. The study also revealed that while lack of expertise and inadequate resource allocation are risks that are prevalent across the three stages, other risks have higher importance during specific phases. Along this line, stakeholder management issues are critical during the planning phase whereas technical and management issues warrant particular attention during the design and procurement phases. The conceptual frameworks developed for each project phase can support practitioners in achieving greater water infrastructure resilience in SIDS by providing a checklist for undertaking risk assessment and guiding project decision-making processes in the ELS.</div></div>","PeriodicalId":54616,"journal":{"name":"Physics and Chemistry of the Earth","volume":"141 ","pages":"Article 104075"},"PeriodicalIF":4.1,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145004504","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

3D U-Net assisted fault probability prediction from seismic volume in Dibrugarh oil field, upper Assam shelf, NE India 3D U-Net辅助印度东北部阿萨姆邦上陆架Dibrugarh油田地震量断层概率预测

IF 4.1 3区地球科学

Physics and Chemistry of the Earth Pub Date : 2025-08-27 DOI: 10.1016/j.pce.2025.104069

Bappa Mukherjee , Soumitra Kar , Kalachand Sain

{"title":"3D U-Net assisted fault probability prediction from seismic volume in Dibrugarh oil field, upper Assam shelf, NE India","authors":"Bappa Mukherjee , Soumitra Kar , Kalachand Sain","doi":"10.1016/j.pce.2025.104069","DOIUrl":"10.1016/j.pce.2025.104069","url":null,"abstract":"<div><div>We presented a novel 3D U-Net Deep Convolutional Neural Network learning-based workflow for predicting the fault probability network from a 3D seismic volume associated with the geologically complex petroliferous basin. The workflow begins with applying a Dip-steered Median Filter (DSMF) to clean the seismic data, followed by Edge-Preserving Smoother (EPS) filter to enhance fault localisation. Subsequently, the Fault Likelihood (FL) attribute is computed from the EPS-filtered volume, followed by the Thin Fault Likelihood (TFL) attribute computation from the FL volume. Further, a fault mask volume was generated through a conditional mathematical attribute from the TFL volume. Two separate deep learning models were trained to predict fault probability networks. The first one utilised DSMF-filtered seismic volumes as input, and the second used EPS-enhanced seismic volumes, while in both cases the corresponding fault mask volume was set as the target. The feasibility of the proposed workflow was tested using 3D seismic data from the Dibrugarh field of the Upper Assam Shelf, India. Both models achieve >85 % accuracy in the training phase and accurately predict faults in the test phase. The EPS volume-based model has a higher accuracy of 89 %. The predicted fault volumes are then passed through a skeletonization filter for more accurate fault localisation. The demonstrated novel fault probability prediction process can predict faults from the voluminous seismic data from structurally complex geological settings with higher accuracy and less computational time. It can apply to the E&P industry's automated subsurface structural interpretation.</div></div>","PeriodicalId":54616,"journal":{"name":"Physics and Chemistry of the Earth","volume":"141 ","pages":"Article 104069"},"PeriodicalIF":4.1,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145105133","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Modeling and prediction of river quality parameters based on a novel hybrid machine learning model 基于新型混合机器学习模型的河流水质参数建模与预测

IF 4.1 3区地球科学

Physics and Chemistry of the Earth Pub Date : 2025-08-27 DOI: 10.1016/j.pce.2025.104067

Parinaz Memar, Saeed Farzin

{"title":"Modeling and prediction of river quality parameters based on a novel hybrid machine learning model","authors":"Parinaz Memar, Saeed Farzin","doi":"10.1016/j.pce.2025.104067","DOIUrl":"10.1016/j.pce.2025.104067","url":null,"abstract":"<div><div>Water pollution in rivers is a major issue, and modeling water quality using machine learning techniques is an effective approach. Total dissolved solids is a key water quality indicator, as improper levels can affect industrial, agricultural, and urban water use. Least Squares Support Vector Machine (LSSVM) algorithms are highly accurate for modeling and predicting water quality parameters, especially when combined with the Crayfish Optimization Algorithm (COA) to enhance prediction accuracy. A study using data from the Jajrood basin (Latiyan, Rodak, and Sharifabad stations) applied LSSVM and LSSVM-COA to model and predict key water quality parameters, including CO<sub>3</sub><sup>−2</sup>, HCO<sub>3</sub><sup>−1</sup>, Cl<sup>−1</sup>, So<sub>4</sub><sup>−2</sup>, Ca<sup>+2</sup>, Mg<sup>+2</sup>, Na<sup>+1</sup> and K<sup>+1</sup>. The accuracy of the results varied, but the LSSVM-COA algorithm was more accurate, particularly at Sharifabad station, where the R values for the combined parameters during testing were 0.92 and the RRMSE was 0.40. Predictive analysis indicated that parameters like Cl<sup>−1</sup>, So<sub>4</sub><sup>−2</sup> and Ca<sup>+2</sup> had the most significant impact on increasing TDS, especially when each parameter's value was increased by 50 %.</div></div>","PeriodicalId":54616,"journal":{"name":"Physics and Chemistry of the Earth","volume":"141 ","pages":"Article 104067"},"PeriodicalIF":4.1,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145004567","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0