Novel ensemble machine learning models in flood susceptibility mapping

Prasad, Pankaj; Loveson, Victor J.; Das, Bappa; Kotha, Mahender

doi:10.1080/10106049.2021.1892209

Cited by 81 publications

(22 citation statements)

References 90 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The algorithm works as follows: (i) At the first step, it adds randomness to the dataframe by shuffling each feature which are called shadow feature (ii) Then, it trains the RF classifier to measure the Z score values and checks whether the attribute has a higher Z score than the maximum Z score among shadow attributes (MZSA). (iii) Finally, the features having value less than MZSA are rejected for being irrelevant and vice versa (Kursa and Rudnicki, 2010;Amiri et al, 2019;Prasad et al, 2021). Shadow minimum, mean, and maximum values represent the Z score of a shadow attribute.…”

Section: Boruta and Multicollinearity Feature Selection Methodsmentioning

confidence: 99%

“…The training dataset defines the model fitness whereas the testing dataset represents the predictive capability of the model (Bui et al, 2018;Prasad et al, 2021). In the case of training dataset, among the six models, the RF performed excellently with the highest value of 1 quantified by accuracy, Kappa, sensitivity, specificity, and AUC in both the primary and secondary study area (Table 4).…”

Section: Performance and Comparison Of The Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Artificial intelligence approaches for spatial prediction of landslides in mountainous regions of western India

et al. 2021

Self Cite

View full text Add to dashboard Cite

The prediction of landslide is a complex task but preparing the landslide susceptibility map through artificial intelligence approaches can reduce life loss and damages resulting from landslides. The purpose of this study is to evaluate and compare the landslide susceptibility mapping (LSM) using six machine learning models, including random forest (RF), deep boost (DB), stochastic gradient boosting (SGB), rotation forest (RoF), boosted regression tree (BRT), and logit boost (LB) in the mountainous regions of western India. The landslide inventory map consisting of 184 landslide locations has been divided into two groups for training (70% dataset) and validation (30% dataset) purposes. Fourteen landslide triggering factors including slope, topographical roughness index, road density, topographical wetness index, elevation, slope length, drainage density, stream power index, geomorphology, rainfall, soil, lithology, lineament density, and normalized difference vegetation index have been considered using the boruta approach for the LSM. The results reveal that the RF model has the highest precision in terms of AUC (0.88; 0.89), kappa (0.62; 0.50), accuracy (0.81; 0.77), and specificity (0.86; 0.86) both in the study region and secondary region, respectively. Hence, it can be concluded that the RF is an effective and promising technique as compared to DB, SGB, RoF, BRT, and LB for landslide susceptibility assessment in the research area as well as in regions having similar geo-environmental configuration.

show abstract

Section: Boruta and Multicollinearity Feature Selection Methodsmentioning

confidence: 99%

Section: Performance and Comparison Of The Modelsmentioning

confidence: 99%

Artificial intelligence approaches for spatial prediction of landslides in mountainous regions of western India

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…NDVI is a good indicator of vegetation coverage, largely inducing soil moisture, evapotranspiration, infiltration, sediment transportation, and runoff. High NDVI minimizes flood events [28] and vice versa. The NDVI layer was prepared from the Sentinel 2B MSI image of 2021 using the NDVI estimation equation (Equation ( 7)).…”

Section: Terrain Distribution Factorsmentioning

confidence: 99%

“…Sachdeva and Kumar [27] employed an ensemble ML approach of an extremely randomized tree model for FHZ mapping with 14 flood conditioning factors for lower Assam, India, in the year 2020. Prasad et al [28] used ensemble ML techniques based on adabag classifiers and AUC with 12 flood-inducing factors for FHZ mapping on the central west coast of India. Novel integration of bootstrapping and random subsampling techniques had high precision for FHZ mapping in Ardabil province, Iran [29].…”

Section: Introductionmentioning

confidence: 99%

Spatial Analysis of Flood Hazard Zoning Map Using Novel Hybrid Machine Learning Technique in Assam, India

et al. 2022

View full text Add to dashboard Cite

Twenty-two flood-causative factors were nominated based on morphometric, hydrological, soil permeability, terrain distribution, and anthropogenic inferences and further analyzed through the novel hybrid machine learning approach of random forest, support vector machine, gradient boosting, naïve Bayes, and decision tree machine learning (ML) models. A total of 400 flood and nonflood locations acted as target variables of the flood hazard zoning map. All operative factors in this study were tested using variance inflation factor (VIF) values (<5.0) and Boruta feature ranking (<10 ranks) for FHZ maps. The hybrid model along with RF and GBM had sound flood hazard zoning maps for the study area. The area under the receiver operating characteristics (AUROC) curve and statistical model matrices such as accuracy, precision, recall, F1 score, and gain and lift curve were applied to assess model performance. The 70%:30% sample ratio for training and validation of the standalone models concerning the AUROC value showed sound results for all the ML models, such as RF (97%), SVM (91%), GBM (97%), NB (96%), DT (88%), and hybrid (97%). The gain and lift curve also showed the suitability of the hybrid model along with the RF, GBM, and NB models for developing FHZ maps.

show abstract

“…Moreover, these models require detailed data at locationsuch as hydro-geomorphological datarequiring intensive calculations and thus making short-term forecasting difficult (Eslaminezhad et al 2022). Previous research has demonstrated that physics-based models only have short-term predictive ability (Eslaminezhad et al 2022;Prasad et al 2022). One final challenge is that the establishment of these models requires a thorough understanding of hydrological parameters (Pham et al 2021f).…”

Section: Introductionmentioning

confidence: 99%

Spatial modeling of flood hazard using machine learning and GIS in Ha Tinh province, Vietnam

Nguyen

2022

Journal of Water and Climate Change

View full text Add to dashboard Cite

The objective of this study was the development of an approach based on machine learning and GIS, namely Adaptive Neuro-Fuzzy Inference System (ANFIS), Gradient-Based Optimizer (GBO), Chaos Game Optimization (CGO), Sine Cosine Algorithm (SCA), Grey Wolf Optimization (GWO), and Differential Evolution (DE) to construct flood susceptibility maps in the Ha Tinh province of Vietnam. The database includes 13 conditioning factors and 1,843 flood locations, which were split by a ratio of 70/30 between those used to build and those used to validate the model, respectively. Various statistical indices, namely root mean square error (RMSE), area under curve (AUC), mean absolute error (MAE), accuracy, and R1 score, were applied to validate the models. The results show that all the proposed models performed well, with an AUC value of more than 0.95. Of the proposed models, ANFIS-GBO was the most accurate, with an AUC value of 0.96. Analysis of the flood susceptibility maps shows that approximately 32–38% of the study area is located in the high and very high flood susceptibility zone. The successful performance of the proposed models over a large-scale area can support local authorities and decision-makers develop policies and strategies to reduce the threats related to flooding in the future.

show abstract

Novel ensemble machine learning models in flood susceptibility mapping

Cited by 81 publications

References 90 publications

Artificial intelligence approaches for spatial prediction of landslides in mountainous regions of western India

Artificial intelligence approaches for spatial prediction of landslides in mountainous regions of western India

Spatial Analysis of Flood Hazard Zoning Map Using Novel Hybrid Machine Learning Technique in Assam, India

Spatial modeling of flood hazard using machine learning and GIS in Ha Tinh province, Vietnam

Contact Info

Product

Resources

About