Novel Ensemble of Multivariate Adaptive Regression Spline with Spatial Logistic Regression and Boosted Regression Tree for Gully Erosion Susceptibility DOI Creative Commons
Paramita Roy, Subodh Chandra Pal, Alireza Arabameri

и другие.

Remote Sensing, Год журнала: 2020, Номер 12(20), С. 3284 - 3284

Опубликована: Окт. 10, 2020

The extreme form of land degradation through different forms erosion is one the major problems in sub-tropical monsoon dominated region. formation and development gullies dominant or active process this So, identification prone regions necessary for escaping type situation maintaining correspondence between spheres environment. goal study to evaluate gully susceptibility rugged topography Hinglo River Basin eastern India, which ultimately contributes sustainable management practices. Due nature data instability, weakness classifier andthe ability handle data, accuracy a single method not very high. Thus, study, novel resampling algorithm was considered increase robustness its accuracy. Gully maps have been prepared using boosted regression trees (BRT), multivariate adaptive spline (MARS) spatial logistic (SLR) with proposed techniques. re-sampling able efficiency all predicted models by improving classifier. Each variable inventory map randomly allocated 5-fold cross validation, 10-fold bootstrap optimism bootstrap, while each consisted 30% database. ensemble model tested 70% validated other K-fold validation (CV) influence random selection training Here, methods are associated higher accuracy, but SLR more optimal than any according robust nature. AUC values BRT MARS 87.40%, 90.40% 90.60%, respectively. According 107,771 km2 (27.51%) area region high susceptible erosion. This potential developmental found primarily Basin, where lateral exposure mainly observed scarce vegetation. outcome work can help policy-makers implement remedial measures minimize damage caused gully.

Язык: Английский

Soil erosion susceptibility assessment using logistic regression, decision tree and random forest: study on the Mayurakshi river basin of Eastern India DOI
Abhishek Ghosh,

Ramkrishna Maiti

Environmental Earth Sciences, Год журнала: 2021, Номер 80(8)

Опубликована: Апрель 1, 2021

Язык: Английский

Процитировано

73
Implementation of Artificial Intelligence Based Ensemble Models for Gully Erosion Susceptibility Assessment DOI Creative Commons
Indrajit Chowdhuri, Subodh Chandra Pal, Alireza Arabameri

и другие.

Remote Sensing, Год журнала: 2020, Номер 12(21), С. 3620 - 3620

Опубликована: Ноя. 4, 2020

The Rarh Bengal region in West Bengal, particularly the eastern fringe area of Chotanagpur plateau, is highly prone to water-induced gully erosion. In this study, we analyzed spatial patterns a potential erosion Gandheswari watershed. This affected by monsoon rainfall and ongoing land-use changes. combination causes intensive land degradation. Therefore, developed susceptibility maps (GESMs) using machine learning (ML) algorithms boosted regression tree (BRT), Bayesian additive (BART), support vector (SVR), ensemble SVR-Bee algorithm. inventory are based on total 178 head-cutting points, taken as dependent factor, conditioning factors, which serve independent factors. We validated ML model results under curve (AUC), accuracy (ACC), true skill statistic (TSS), Kappa coefficient index. AUC result BRT, BART, SVR, models 0.895, 0.902, 0.927, 0.960, respectively, show very good GESM accuracies. provides more accurate prediction than any single used study.

Язык: Английский

Процитировано

72
Evaluation of different DEMs for gully erosion susceptibility mapping using in-situ field measurement and validation DOI
Indrajit Chowdhuri, Subodh Chandra Pal, Asish Saha

и другие.

Ecological Informatics, Год журнала: 2021, Номер 65, С. 101425 - 101425

Опубликована: Сен. 11, 2021

Язык: Английский

Процитировано

65
Optimization modelling to establish false measures implemented with ex-situ plant species to control gully erosion in a monsoon-dominated region with novel in-situ measurements DOI
Asish Saha, Subodh Chandra Pal, Alireza Arabameri

и другие.

Journal of Environmental Management, Год журнала: 2021, Номер 287, С. 112284 - 112284

Опубликована: Март 9, 2021

Язык: Английский

Процитировано

60
Flood susceptibility mapping using meta-heuristic algorithms DOI Creative Commons
Alireza Arabameri, Amir Seyed Danesh,

M. Santosh

и другие.

Geomatics Natural Hazards and Risk, Год журнала: 2022, Номер 13(1), С. 949 - 974

Опубликована: Апрель 11, 2022

Flood is a common global natural hazard, and detailed flood susceptibility maps for specific watersheds are important management measures. We compute the map Kaiser watershed in Iran using machine learning models such as support vector (SVM), Particle swarm optimization (PSO), genetic algorithm (GA) along with ensembles (PSO-GA SVM-GA). The application of assessment mapping analyzed, future research suggestions presented. model was constructed based on fifteen causatives: slope, slope aspect, elevation, plan curvature, land use, cover, normalize differences vegetation index (NDVI), convergence (CI), topographical wetness (TWI), topographic positioning Index (TPI), drainage density (DD), distance to stream, terrain ruggedness (TRI), surface texture (TST), geology stream power (SPI) inventory data which later divided by 70% training 30% validated model. output evaluated through sensitivity, specificity, accuracy, precision, Cohen Kappa, F-score, receiver operating curve (ROC). evaluation method shows robust results from (0.839), particle (0.851), (0.874), SVM-GA (0.886), PSO-GA (0.902). Compared have done some methods commonly used this assessment. A high-quality, informative database essential classification types that very helpful improve performances. performance ensemble better than model, yielding high degree accuracy (AUC-0.902%). Our approach, therefore, provides novel studies other watersheds.

Язык: Английский

Процитировано

57
Testing the performances of different fuzzy overlay methods in GIS-based landslide susceptibility mapping of Udi Province, SE Nigeria DOI Open Access
Vincent E. Nwazelibe, Chinanu O. Unigwe, Johnbosco C. Egbueri

и другие.

CATENA, Год журнала: 2022, Номер 220, С. 106654 - 106654

Опубликована: Сен. 28, 2022

Язык: Английский

Процитировано

42
Geospatial assessment of soil erosion in the Basantar and Devak watersheds of the NW Himalaya: A study utilizing USLE and RUSLE models DOI Creative Commons
Ajay Kumar Taloor, Varun Khajuria, Gurnam Parsad

и другие.

Geosystems and Geoenvironment, Год журнала: 2025, Номер unknown, С. 100355 - 100355

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

1
GIS and remote sensing-based assessment of soil erosion risk using RUSLE model in South-Kivu province, eastern, Democratic Republic of Congo DOI Creative Commons
Luc Cimusa Kulimushi, Pandurang Choudhari, Léonard Mubalama

и другие.

Geomatics Natural Hazards and Risk, Год журнала: 2021, Номер 12(1), С. 961 - 987

Опубликована: Янв. 1, 2021

Soil erosion risk assessment in South-Kivu longs for the colonial epoch, while province faces problem of extreme degradation land form soil erosion. Thus, study attempts to assess at level using Revised Universal Loss Equation (RUSLE) conjunction with Geographical Information System (GIS), and remote sensing data. The estimated total was 2.084 million tons; an annual average 138.2 t ha−1 yr−1. Moreover, loss greater than 100 yr−1 accounts 45.2% erosive land. worsening nearly entire territories range between 87 Shabunda 248 Uvira. Under high aggressiveness rainfall mean 1857.19 mm/y, highest rate found Perennial crop, Trees, Cropland contrast Shrub closed Forest mainly due slope 22% former Land cover categories compared 17% Shrubland forest. adoption terracing could reduce by 76% current cropland i.e., from (162.12 38 yr−1). Therefore it is strongly recommended.

Язык: Английский

Процитировано

53
Comparison of multi-criteria and artificial intelligence models for land-subsidence susceptibility zonation DOI
Alireza Arabameri, Subodh Chandra Pal, Fatemeh Rezaie

и другие.

Journal of Environmental Management, Год журнала: 2021, Номер 284, С. 112067 - 112067

Опубликована: Фев. 7, 2021

Язык: Английский

Процитировано

48
Drought risk assessment: integrating meteorological, hydrological, agricultural and socio-economic factors using ensemble models and geospatial techniques DOI
Alireza Arabameri, Subodh Chandra Pal,

M. Santosh

и другие.

Geocarto International, Год журнала: 2021, Номер 37(21), С. 6087 - 6115

Опубликована: Июнь 25, 2021

Among natural disasters, drought hits almost half of the world every year, regardless climatic zones. Identifying vulnerability regions is fundamental to plan and adopt mitigation measures. Here we apply a multi-criteria-based machine learning technique that integrates spatial data for preparing map different categories. We adopted remote sensing tools with three models namely support vector (SVM), random forest (RF) regression (SVR) their ensembles (i.e. Bagging, Boosting Stacking), as applied northwestern part Iran case study. Various types geo-environmental factors were considered including meteorological, hydrological, agricultural socio-economic. The result model was evaluated through arithmetic logic values (area under curve [AUC]) receiver operating (ROC). Through multi-collinearity test, prominent causative occurrences are defined. AUC value from ROC SVR-Stacking, RF-Stacking SVM-Stacking training datasets 0.942, 0.918 0.896, respectively. SVR-Stacking yielded best (AUC = 0.94) confirming SVR serves robust preparation susceptibility maps can be used by governmental other administrative agencies.

Язык: Английский

Процитировано

48