Assessment of the Effect of Training Data Selection on Landslide Susceptibility Mapping DOI

Hanupriya Deora,

Drishti Gupta,

Kush Gupta

et al.

Published: Dec. 29, 2023

Landslide susceptibility mapping is a component of geo hazard assessment and mitigation planning. This study focuses on analyzing studying the impact training data accuracy reliability landslide maps. We analyze different parameters, including size, spatial distribution, diversity, performance machine learning models employed for modeling. utilize multiple set comprising geological, topographical, climatic, many other variables to develop models. Our findings reveal that selection significantly affects model's pre dictive capabilities, with implications both false positive negative rates in prediction. provides insights into optimizing strategies more accurate mapping, thereby contributing geohazard assessment. occurrences during rainy seasons pose significant challenges Himalayan region hilly areas India. Nevertheless, there lack sufficient research pertaining landslides these vulnerable regions.

Language: Английский

Groundwater quality evaluation using hybrid model of the multi-layer perceptron combined with neural-evolutionary regression techniques: case study of Shiraz plain DOI
Hossein Moayedi, Marjan Salari, Atefeh Ahmadi Dehrashid

et al.

Stochastic Environmental Research and Risk Assessment, Journal Year: 2023, Volume and Issue: 37(8), P. 2961 - 2976

Published: April 1, 2023

Language: Английский

Citations

30
Novel evolutionary-optimized neural network for predicting landslide susceptibility DOI
Rana Muhammad Adnan Ikram, Imran Khan, Hossein Moayedi

et al.

Environment Development and Sustainability, Journal Year: 2023, Volume and Issue: 26(7), P. 17687 - 17719

Published: May 19, 2023

Language: Английский

Citations

24
A new combined approach of neural-metaheuristic algorithms for predicting and appraisal of landslide susceptibility mapping DOI
Hossein Moayedi, Atefeh Ahmadi Dehrashid

Environmental Science and Pollution Research, Journal Year: 2023, Volume and Issue: 30(34), P. 82964 - 82989

Published: June 19, 2023

Language: Английский

Citations

24
A new procedure for optimizing neural network using stochastic algorithms in predicting and assessing landslide risk in East Azerbaijan DOI
Atefeh Ahmadi Dehrashid, Hailong Dong,

Marieh Fatahizadeh

et al.

Stochastic Environmental Research and Risk Assessment, Journal Year: 2024, Volume and Issue: unknown

Published: March 21, 2024

Language: Английский

Citations

7
Flood hazard mapping using GIS-based statistical model in vulnerable riparian regions of sub-tropical environment DOI Creative Commons

Anitabha Ghosh,

Uday Chatterjee, Subodh Chandra Pal

et al.

Geocarto International, Journal Year: 2023, Volume and Issue: 38(1)

Published: Nov. 20, 2023

Floods are a recurrent natural calamity that presents substantial hazards to human lives and infrastructure. The study indicates significant proportion of the area, specifically 27.05%, is classified as moderate flood risk zone (FRZ), while 20.78% designated high or very FRZ. region's low FRZ at 52.17%. GIS-based AHP model demonstrated exceptional predictive precision, achieving score 0.749 (74.90%) determined by AUC-ROC, widely used statistical evaluation tool. current has identified areas with in affected CD blocks, which situated low-lying plains, regions gentle slopes, drainage density, TWI, NDVI, MNDWI, population intensive agricultural land. findings this research offer perspectives for decision-makers, city planners, emergency management agencies devising efficient measures mitigate risks.

Language: Английский

Citations

15
Assessment of sodium adsorption ratio (SAR) in groundwater: Integrating experimental data with cutting-edge swarm intelligence approaches DOI

Zongwang Wu,

Hossein Moayedi, Marjan Salari

et al.

Stochastic Environmental Research and Risk Assessment, Journal Year: 2024, Volume and Issue: unknown

Published: April 29, 2024

Language: Английский

Citations

5
Evaluation of student failure in higher education by an innovative strategy of fuzzy system combined optimization algorithms and AI DOI Creative Commons

Junting Nie,

Hossein Ahmadi Dehrashid

Heliyon, Journal Year: 2024, Volume and Issue: 10(7), P. e29182 - e29182

Published: April 1, 2024

This research suggests two novel metaheuristic algorithms to enhance student performance: Harris Hawk's Optimizer (HHO) and the Earthworm Optimization Algorithm (EWA). In this sense, a series of adaptive neuro-fuzzy inference system (ANFIS) proposed models were trained using these methods. The selection best-fit model depends on finding an excellent connection between inputs output(s) layers in training testing datasets (e.g., combination expert knowledge, experimentation, validation techniques). study's primary result is division participants into performance-based groups (failed non-failed). experimental data used build measured fourteen process variables: relocation, gender, age at enrollment, debtor, nationality, educational special needs, current tuition fees, scholarship holder, unemployment, inflation, GDP, application order, day/evening attendance, admission grade. During evaluation, scoring was created addition mean absolute error (MAE), square (MSE), area under curve (AUC) assess efficacy utilized approaches. Further revealed that HHO-ANFIS superior EWA-ANFIS. With AUC = 0.8004 0.7886, MSE 0.62689 0.65598, MAE 0.64105 0.65746, failure pupils assessed with most significant degree accuracy. MSE, MAE, precision indicators showed EWA-ANFIS less accurate, having amounts 0.71543 0.71776, 0.70819 0.71518, 0.7565 0.758. It found optimization have high ability increase accuracy performance conventional ANFIS predicting students' performance, which can cause changes management improve quality academic programs.

Language: Английский

Citations

4
Advancing Landslide Susceptibility Mapping in the Medea Region Using a Hybrid Metaheuristic ANFIS Approach DOI Creative Commons
Fatiha Debiche, Mohammed Amin‎ Benbouras, Alexandru-Ionuţ Petrişor

et al.

Land, Journal Year: 2024, Volume and Issue: 13(6), P. 889 - 889

Published: June 19, 2024

Landslides pose significant risks to human lives and infrastructure. The Medea region in Algeria is particularly susceptible these destructive events, which result substantial economic losses. Despite this vulnerability, a comprehensive landslide map for lacking. This study aims develop novel hybrid metaheuristic model the spatial prediction of susceptibility Medea, combining Adaptive Neuro-Fuzzy Inference System (ANFIS) with four optimization algorithms (Genetic Algorithm—GA, Particle Swarm Optimization—PSO, Harris Hawks Optimization—HHO, Salp Algorithm—SSA). modeling phase was initiated by using database comprising 160 occurrences derived from Google Earth imagery; field surveys; eight conditioning factors (lithology, slope, elevation, distance stream, land cover, precipitation, slope aspect, road). Afterward, Gamma Test (GT) method used optimize selection input variables. Subsequently, optimal inputs were modeled ANFIS techniques their performance evaluated relevant statistical indicators. comparative assessment demonstrated superior predictive capabilities ANFIS-HHO compared other models. These results facilitated creation an accurate map, aiding use managers decision-makers effectively mitigating hazards similar ones across world.

Language: Английский

Citations

4
A novel evolutionary combination of artificial intelligence algorithm and machine learning for landslide susceptibility mapping in the west of Iran DOI
Yue Shen, Atefeh Ahmadi Dehrashid,

Ramin Atash Bahar

et al.

Environmental Science and Pollution Research, Journal Year: 2023, Volume and Issue: 30(59), P. 123527 - 123555

Published: Nov. 21, 2023

Language: Английский

Citations

10
Research on Slope Stability Prediction Based on MC-BKA-MLP Mixed Model DOI Creative Commons
Yan Lu, Hongze Zhao

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(6), P. 3158 - 3158

Published: March 14, 2025

Quantifying slope mechanical parameters as comprehensive indicators is crucial for predicting stability. The Mohr–Coulomb (M-C) criterion, a classical method determining the relevant of rock mass mechanics, effectively reflects failure characteristics masses in most types slopes. Based on this, effective stress and shear strength from M-C criterion are selected key indicators, characteristic dataset constructed by integrating these with other influencing factors safety factor, calculated using Bishop within framework limit equilibrium analysis, serves output variable. Subsequently, novel Black Kite Algorithm (BKA) was developed to enhance prediction model multilevel perceptron neural network. results demonstrate that mean square error (RMSE) BKA-MLP merely 2.41%, significantly lower than alternative models. Additionally, R2 value reaches approximately 95%, indicating high level interpretability. SHAP-based interpretability analysis trained highlights stress, strength, angle three sensitive features. findings, targeted landslide prevention measures were proposed, providing new approach stability disaster prevention.

Language: Английский

Citations

0