Arabian Journal of Geosciences最新文献

{"title":"Application of multiple machine learning algorithms for intelligent prediction of the strength of fine-grained natural soils","authors":"Muhammad Shahroz Khalid,&nbsp;Zia ur Rehman,&nbsp;Badee Alshameri,&nbsp;Zain Maqsood,&nbsp;Fazal Hussain,&nbsp;Muhammad Irslan Khalid,&nbsp;Syed Jamal Arbi,&nbsp;Abbas Haider","doi":"10.1007/s12517-025-12236-y","DOIUrl":"10.1007/s12517-025-12236-y","url":null,"abstract":"<div><p>This study presents a novel intelligent approach for predicting the unconfined compressive strength (UCS) of fine-grained natural soils by utilizing machine learning (ML) techniques such as Gradient Boost (GB), random forest (RF), and Extreme Gradient Boost (XGB) on a large dataset obtained from multiple sources. A comprehensive testing initiative was conducted to assess the UCS, sieve analysis, Atterberg limits, and specific gravity of natural soils. To overcome the limitations of existing UCS predictive models in covering output variability for the fine-grained natural soil deposit, a diversity of input parameters defining natural soil attributes, such as the percentage of fines, sand, plasticity index (PI), specific gravity (Gs), and liquid limit (LL), were employed. Multiple ML models were developed through Python code with varying algorithm inputs, and the models with the best predicting abilities were analyzed. The ability of the ML models to predict based on the number of statistical performance indices (SPIs) such as correlation indices, i.e., coefficient of determination (<i>R</i>²), Nash–Sutcliffe efficiency (NSE), and Pearson correlation coefficient (PCC); and error indices, i.e., root mean square error (RMSE), Willmott index (WI), and mean absolute error (MAE), were analyzed and found to be reasonable based on SPIs. Based on the rank analysis of SPIs, the XGB model was proposed to predict the UCS value of natural soils. Sensitivity and parametric analyses revealed that LL has the most significant effect on prediction in the proposed model, pursued by PI, fines, sand, and Gs. The proposed XGB approach is a potentially effective asset to geologists and engineers to predict the UCS for new datasets of natural soils and liquid limits ranging between 20 and 40.</p></div>","PeriodicalId":476,"journal":{"name":"Arabian Journal of Geosciences","volume":"18 5","pages":""},"PeriodicalIF":1.827,"publicationDate":"2025-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143875293","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":"Integrating unsaturated soil mechanics for sustainable landslide mitigation strategies","authors":"Monir Hossain,&nbsp;Tanvir Hasan,&nbsp;Shoma Hore,&nbsp;Abul Khair,&nbsp;Ripon Hore","doi":"10.1007/s12517-025-12259-5","DOIUrl":"10.1007/s12517-025-12259-5","url":null,"abstract":"<div><p>Rain-induced landslides and slope instability pose significant threats in mountainous regions with deep water tables, including the hilly tracts of Bangladesh, where unique geological compositions and soil properties exacerbate these risks. This study offers a comprehensive characterization of unsaturated soils, focusing on laboratory measurements such as the soil–water characteristic curve (SWCC), permeability (<i>k</i>) function, saturated permeability (<i>k</i>_sat), and suction-monitored direct shear tests, with particular emphasis on low plastic silty clay (CL-ML) soil types. The implementation of a multilayer covering system (MLCS) with a capillary barrier system to prevent precipitation infiltration into residual soil slopes demonstrates the application of unsaturated soil mechanics theories. Moreover, the study investigates the role of vegetation, specifically live stakes, in reinforcing slope stability. Laboratory and numerical analyses of a typical slope in the Chittagong Hills region reveal that the factor of safety (FS) against slope failure with the deployment of MLCS reaches 1.25 following 72-h rainfall events with an intensity of 1.2 × 10⁻⁶ m/s (106 mm/day), whereas the FS for the natural slope falls below 1.0. This research yields valuable insights into regional soil properties and presents sustainable solutions that integrate engineering and bioengineering concepts to effectively mitigate rain-induced slope failures in mountainous areas.</p></div>","PeriodicalId":476,"journal":{"name":"Arabian Journal of Geosciences","volume":"18 5","pages":""},"PeriodicalIF":1.827,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871310","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":"Evolution of the lithospheric mantle under Boulaye volcano inferred from ultramafic lherzolite xenoliths (Adamawa plateau, Cameroon, Central Africa)","authors":"Sahabo Abobakar Abdoulaye,&nbsp;Okomo Atouba Lise Carole,&nbsp;Bardintzeff Jacques-Marie,&nbsp;Ombolo Auguste,&nbsp;Nkouandou Oumarou Faarouk,&nbsp;Fagny Mefire Aminatou,&nbsp;Adama Haman,&nbsp;Njankouo Ndassa Zénab Nouraan,&nbsp;Dourwe Dogsaye Pierre,&nbsp;Feukam Feuto Joël B.,&nbsp;Niraka Voundou Dieudonné,&nbsp;Bonin Bernard,&nbsp;Pouclet André","doi":"10.1007/s12517-025-12224-2","DOIUrl":"10.1007/s12517-025-12224-2","url":null,"abstract":"<div><p>This paper presents new data on mineral chemistry of ultramafic xenoliths from the Boulaye volcanic area, Adamawa plateau in Central Africa. Modal composition (olivine + orthopyroxene + clinopyroxene + spinel + amphibole) indicates spinel lherzolite with protogranular and porphyroclastic textures. Electron microprobe mineral analyses show that olivine is high Fo with variable CaO contents, orthopyroxene is calcium enstatite, clinopyroxene is Cr-diopside and spinel is Cr-spinel. Variations of contents in some major elements exhibited by olivine, pyroxene and spinel denote increasingly large degrees of melt depletion, emphasizing the complex tectono-magmatic history of the Adamawa lithosphere mantle. Xenoliths are equilibrated between 1027 and 1102 °C within pressure range of 0.9 to 1.7 GPa at equilibrium depths of 30 to 56 km. Boulaye xenoliths stand as mantle residues whose evolution is governed by melt extraction process (5 to 20%) overprinted by Ti–rich metasomatic fluid and/or melt. The geodynamic settings involve a Pan-African subduction event prior to upwelling of Adamawa lithospheric mantle, due to Pan-African strike-slip fault activity at Tertiary times.</p></div>","PeriodicalId":476,"journal":{"name":"Arabian Journal of Geosciences","volume":"18 5","pages":""},"PeriodicalIF":1.827,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143861415","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":"Integrated geophysical and hydrogeological techniques for environmental monitoring and assessment: a case study for waste disposal site, Jeddah Saudi, Arabia","authors":"Faisal Rehman,&nbsp;Helmy S. O. Abuelnaga,&nbsp;Hussein M. Harbi,&nbsp;Tahir Azeem,&nbsp;Jamil Siddique,&nbsp;Omar Riaz,&nbsp;Muhammad Fahad Ullah,&nbsp;Faisal Rehman","doi":"10.1007/s12517-025-12245-x","DOIUrl":"10.1007/s12517-025-12245-x","url":null,"abstract":"<div><p>Environmental problems are inevitable phenomena for worldwide. Nowadays in multidisciplinary research era, integrated geophysical techniques are commonly applied for environmental monitoring and assessment along with other techniques. Waste disposal is an alarming problem and causes a lot of environmental issue. In Jeddah City, residential and industrial waste was deposited without treatment et al. Misk (Buraiman) Lake. Geophysical and hydrological investigations were carried out to identify and monitor extent of the contamination in the subsurface. Geophysical techniques comprised of electromagnetic induction and electrical resistivity methods. The hydrogeological investigations included water sample analysis. High electrical conductivity values were observed along the plume compared to the surroundings. The results of the electromagnetic survey, electrical resistivity and water samples were correlated and found in good agreement. The contamination was found in most of the areas with varying concentration levels. The study revives that integrating geophysical techniques with hydrogeological studies eases to map the groundwater contamination.\u0000</p></div>","PeriodicalId":476,"journal":{"name":"Arabian Journal of Geosciences","volume":"18 5","pages":""},"PeriodicalIF":1.827,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143856631","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":"Geo-hydrological analysis and watershed delineation of the Sarayan River, Ganga Plain, India: integrating geospatial data for water resource management","authors":"Pawan Kumar Gautam,&nbsp;Narendra Kumar","doi":"10.1007/s12517-025-12255-9","DOIUrl":"10.1007/s12517-025-12255-9","url":null,"abstract":"<div><p>This study focuses on the drainage parameters and basin characteristics of the Sarayan basin using geospatial techniques. The Sarayan basin is situated in the interfluve region of the Gomati and Ghaghara River within the Middle Ganga Plain. It is the left tributary of the Gomati River that flows within the Ganga Plain of Uttar Pradesh, India. Various parameters, including linear, areal, relief, geometric, and morpho-tectonic, were calculated to assess the basin’s shape, drainage pattern, and topographical characteristics. It is classified as a fifth-order stream. It exhibits a dendritic type of drainage pattern that covers an area of 1695 km². The analysis reveals the basin characteristics by a mature alluvial river system, dendritic drainage pattern, indicating homogeneity in texture and underlying geology and stable geomorphic conditions. Linear parameters indicate a gentle ground slope and minimal soil erosion within the basin. Areal parameters further emphasize smooth topography, low runoff potential, gentle slope, lower susceptibility to soil erosion, efficient infiltration, and enhanced permeability, resulting in prolonged flow paths that facilitate effective groundwater recharge processes. Morphtectonic parameters, including the sinuosity index (1.60), reveal diverse levels of channel sinuosity within the basin. Values ranging from 1.07 to 1.27 signify low sinuosity, while those between 1.31 and 1.44 suggest heightened sinuosity and lateral erosion. A SI of 1.50 and 1.82 indicates various degrees of river meandering and lateral erosion. Additionally, the asymmetry factor (59) indicates channel migration towards the east. The hypsometric integrals (0.50) suggest a mature landscape characterized by a low stage of incision and minimal sediment transport. In summary, the study presents a comprehensive analysis of the Sarayan River drainage and basin characteristics, shedding light on its hydrological dynamics and geomorphic evolution within the Ganga Plain.\u0000</p></div>","PeriodicalId":476,"journal":{"name":"Arabian Journal of Geosciences","volume":"18 5","pages":""},"PeriodicalIF":1.827,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143830725","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":"Application of remote sensing in the identification and analysis of lineaments for groundwater exploration using Landsat-8 Oli and SRTM data in Ebolowa and environs","authors":"Njifontawouo Ouzerou Mimche,&nbsp;Anatole Eugene Djieto Lordon,&nbsp;Charles Antoine Basseka,&nbsp;Christ Alain Nekuie Mouafo,&nbsp;Yannick Stephan Kengne","doi":"10.1007/s12517-025-12249-7","DOIUrl":"10.1007/s12517-025-12249-7","url":null,"abstract":"<div><p>This research aimed to identify and analyse lineaments for groundwater exploration and delineate possible zones for groundwater exploitation. To achieve this, Landsat-8 OLI spectral bands as well as SRTM data covering the study area were obtained from the United States Geological Survey (USGS) website, from which fracture maps were produced. The extraction method of lineaments from remote sensing data required some pre-processing of the Landsat satellite image spectral bands to reduce the effect of the atmosphere and geometric distortions during data acquisition. The automatic lineament extraction was performed with the PCI Geomatica 2016 software for Landsat images and manually for SRTM on ArcGIS. Automatic lineament extraction was applied to the PC1 and PC2 bands of the Landsat-8 OLI image and each of the four shaded relief images of the SRTM images (N0°, N45°, N90°, and N135°). The results reveal 909 lineaments ranging from 21 m to 10.1 km, with an average length of 1.98 km and a standard deviation of 1.27. The lineaments on directional maps and rose diagrams show 8 directions with the predominance NE-SW. The secondary directions are NW–SE and WNW-ESE. The results are validated by the structural data measured in the field, the geological map of Cameroon, the hydrographic network, and the slope map. The results show an important role played by fractures in the occurrence of underground water in the study area. All this has enabled us to identify and characterise the potential areas for groundwater exploitation.\u0000</p></div>","PeriodicalId":476,"journal":{"name":"Arabian Journal of Geosciences","volume":"18 5","pages":""},"PeriodicalIF":1.827,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143821780","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":"New constraints on tectonic inversion–based Orogeny of Western Kopet-dagh (NE of Iran)","authors":"Rezvaneh Hamidi,&nbsp;Hojjat Ollah Safari,&nbsp;Arash Amini","doi":"10.1007/s12517-025-12253-x","DOIUrl":"10.1007/s12517-025-12253-x","url":null,"abstract":"<div><p>One of the orogen types in the intra-continental tectonic settings is pop-up structures with bi-vergent thrust tectonics. In this research, the western part of the Kopet-dagh Orogen, as the southern boundary of the Turan Plate, is selected as a case study for investigation on tectonic development and deformation patterns, using surface–subsurface structural studies together with complementary remote sensing and GIS environmental capability as a multi-disciplinary approach. The results of this research determined two sets of faults, consisting of (a) first-stage longitudinal reverse faults with a structural trend of N90–100 to N50–70 (Tangrah, Takal-Kuh, Marave-Tappe, and Golijeh faults), and (b) transversal right-hand strike-slip faults with a trend of N130–150 (Kalaleh, Ughcheh, and Sarighamish faults). These two sets of faults formed the structural framework of this zone and played an important role in the tectonic evolution (initiation, shaping, evolution of sedimentary basins, and forming a fold-thrust belt) of this orogen. A change in the mechanism of the first-stage longitudinal faults, as tectonic inversion, at the onset of the Late Alpine Orogeny caused the re-arrangement of P-axes and thus formed bi-vergent reverse faulting in the northern and southern edges of this zone. Subsequently, fault propagation folds were established due to this event. Finally, an extensive V-shaped compressional pop-up structure with bi-vergent thrusting and fold axial surfaces (as fault-related folds) was formed in the Kopet-dagh fold-thrust belt. Also, the mechanism of the second-stage transversal faults changed to right-hand strike-slip faults with some normal components at the onset of the Late Alpine Orogeny. The normal component of these faults (especially the Kalaleh fault) caused the settlement of the western part of this zone along them and formed the Gorgan-Gonbad plain.</p><h3>Graphical abstract</h3><div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>","PeriodicalId":476,"journal":{"name":"Arabian Journal of Geosciences","volume":"18 5","pages":""},"PeriodicalIF":1.827,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143821779","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":"Analysis of land cover change on soil organic carbon stock for detecting environmental degradation in Nigeria landscape","authors":"Anthony Tobore,&nbsp;Ugonna Nkwunonwo,&nbsp;Ganiyu Oyerinde,&nbsp;Babatunde Fagbohun,&nbsp;Olayinka Olaewe,&nbsp;Emmanuel Anoke,&nbsp;Faith Oyedokun","doi":"10.1007/s12517-025-12254-w","DOIUrl":"10.1007/s12517-025-12254-w","url":null,"abstract":"<div><p>The analysis of land cover change (LCC) is among the pressing environmental solutions for assessing location-specific information on soil organic carbon (SOC) stocks. The objective of this study was to investigate the impact of LCC on SOC stocks in Ewekoro, Nigeria, using remote-sensing techniques. Thirty clustered soil samples (0–30 cm) analyzed for SOC and bulk density were subjected to the kriging method. LCC maps for the years 2004, 2014, and 2024 were generated using a support vector machine (SVM) algorithm, incorporating spectral environmental indicators including the digital elevation model (DEM), normalized difference vegetation index (NDVI), and salinity index (SI) from Landsat 7 and 8 satellite images. The study showed a significant increase (0.6%) in the barelands from 2004 (1.4%) to 2024 (36.9%), followed by a substantial increase in built-up areas. In contrast, vegetation cover declined drastically (26.1%), followed by wetlands (1.6%), and water bodies (1.4%). SOC stock values of the area ranged between 16.7 (low) and 77.2 (high) t ha⁻¹ with a mean of 32.8 t ha⁻¹. The findings from this study call for an urgent need to alert policymakers around population growth to step up adaptation and mitigation interventions to balance development and environmental preservation in this climate-vulnerable landscape.</p></div>","PeriodicalId":476,"journal":{"name":"Arabian Journal of Geosciences","volume":"18 5","pages":""},"PeriodicalIF":1.827,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143818247","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":"Calcareous nannofossil micropalaeontology of the Eocene–Oligocene offshore sedimentary sequence of the Mannar Basin, Sri Lanka: deciphering palaeoenvironmental dynamics of the equatorial margin of the Northern Indian Ocean","authors":"Nethmi Wickramarathna,&nbsp;Prasanna Lakshitha Dharmapriya,&nbsp;Nuwan Sanjaya Wanniarachchi,&nbsp;Babu Ram Gyawali,&nbsp;Chandramali Jayawardana,&nbsp;Sachini Nawarathne,&nbsp;Apsara Umayangani Wijenayake,&nbsp;Chaminda Kularathna","doi":"10.1007/s12517-025-12227-z","DOIUrl":"10.1007/s12517-025-12227-z","url":null,"abstract":"<div><p>The Eocene–Oligocene transition (EOT) marks a pivotal shift from a global warm climate to the glaciated conditions observed in the Oligocene Era. Despite its significance, research on the palaeoenvironmental and palaeoclimatic conditions during this transition in the equatorial margin of the Northern Indian Ocean around Sri Lanka remains limited. This study addresses this gap by reconstructing these conditions using calcareous nannoplankton assemblages from sediment cores collected in the Mannar Basin in the Indian Ocean. A total of 54 species spanning 17 genera and 7 families were identified, indicative of a diverse marine ecosystem during this period. The assemblages were distributed across NP23 to NP16 nannofossil zones, corresponding to the Bartonian to early Rupelian stages. Warm-water species such as <i>Coccolithus pelagicus</i> and <i>Umbilicosphaera bramlettei</i>, alongside cold-water species like <i>Reticulofenestra dictyoda</i>, suggest variations in sea surface temperatures and cooler water layers or upwelling zones. The rapid extinction of warm-water taxa and the absence of certain species during the Eocene–Oligocene Transition indicate a significant decrease in temperature. Notably, the decline in abundance of k-mode taxa such as Coccolithus, Discoaster and Ericsonia suggests a shift from warm and oligotrophic conditions to cooler and eutrophic environments. Key index nannofossils, including <i>Coccolithus formosus</i> and <i>Discoaster deflandrei</i>, indicate relatively high sea surface temperatures and oligotrophic environments. These findings shed light on the transition from the late Eocene to the early Oligocene period and provide valuable insights into past climatic and environmental dynamics in the Indian Ocean.</p></div>","PeriodicalId":476,"journal":{"name":"Arabian Journal of Geosciences","volume":"18 5","pages":""},"PeriodicalIF":1.827,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143809094","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":"Investigation of the effect of climatic parameters in machine learning algorithms for streamflow predicting in Hamoon Helmand Catchment, Iran","authors":"Shabnam Vakili,&nbsp;Seyyed Morteza Mousavi","doi":"10.1007/s12517-025-12243-z","DOIUrl":"10.1007/s12517-025-12243-z","url":null,"abstract":"<div><p> The objective of this study is to identify the effective input parameters for estimating streamflow using an M5 model tree and Genetic Algorithm (GA) and Long Short-Term Memory (LSTM) and to propose a dependable model. These methods were chosen for their ability to model complex relationships, high prediction accuracy, and efficient input optimization capabilities. The study utilized monthly data of rainfall, temperature, evaporation, and streamflow for the latest month (Q_t-1) and the preceding 2 months (Q_t-2) in the Hamoon Helmand catchment. Five scenarios were employed in M5 and the linear and nonlinear models of GA and LSTM. The models’ performance was assessed using statistical parameters such as RMSE, MAE, R, and NSE. In the initial scenario where all five parameters were considered, M5, the linear and nonlinear GA models and LSTM produced the most accurate results, with RMSE values of 9.27, 6.87, 5.54, and 5.55, respectively. The second scenario (rainfall; maximum, minimum, and average temperatures; Q_t-1 (discharge for 1 month before) and evaporation) revealed that the linear and nonlinear GA models, with RMSE values of 7.21 and 6.55, respectively, were more accurate than M5 and LSTM with an RMSE value of 8.58 and 6.78, respectively. In Scenarios 3 (rainfall; average temperatures; evaporation; and Q_t-1, Q_t-2 (discharge for 1, 2 months before)) and 4 (rainfall; average temperatures; Q_t-1, Q_t-2 (discharge for 1, 2 months before)), LSTM demonstrated superior performance. The results obtained from Scenario 5 (rainfall; maximum, minimum, and average temperatures and evaporation) indicate that in the absence of sufficient runoff data in a basin, there is no necessity to employ a nonlinear model; instead, modeling with an M5 model tree yields sufficiently accurate results. This research demonstrates the global significance of optimizing water resource management models in arid and climate-sensitive regions and contributes to the resilience and sustainability of resources in the face of climate change.</p></div>","PeriodicalId":476,"journal":{"name":"Arabian Journal of Geosciences","volume":"18 5","pages":""},"PeriodicalIF":1.827,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143801171","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}