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

Abstract

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.

Spatiotemporal Flood Hazard Map Prediction Using Machine Learning for a Flood Early Warning Case Study: Chiang Mai Province, Thailand

“…Non-deterministic methods, including both statistical and machine learning approaches, are useful for developing predictive solutions in classification. Statistical methods like the analytical hierarchy process (AHP) [10], logistic regression (LR) [11], and frequency ratio (FR) [12], as well as machine learning methods like support vector machines (SVMs) [13], random forest (RFs) [14], and convolutional neural networks (CNNs) [15], are widely utilized for this purpose.…”

Recent Trends of Machine Learning Techniques on The Growth of Agricultural Sector of Assam

“…Numerous machine learning models are employed to delineate flood-prone areas and assess the health of tea leaves, facilitating proactive management [35][36][37]. Simultaneously, artificial intelligence systems forecast alternative crops based on soil and climate data, aiming to optimize land utilization and minimize associated risks [32][33][34] Not specified in the provided information [27] Not specified Review of evapotranspiration approaches and concepts.…”

Prioritizing sub-watersheds for soil erosion using geospatial techniques based on morphometric and hypsometric analysis: a case study of the Indian Wyra River basin

“…It is appropriate to use the watershed technique to investigate different processes occurring at the surface of the ground, which is an area of the ground where the primary discharge is transferred to a single exit (Pande and Moharir 2017;Pande et al 2020). Watersheds, or hydrological units, are regarded to be more efficient and appropriate for conducting necessary surveys and investigations, as well as planning and implementing various improvement initiatives including water and soil conservation, and assuring their long-term viability (Singha et al 2022;Poongodi and Venkateswaran 2018;Shekar and Mathew 2022a;Krishnan et al 2017). Therefore, watershed management should be given special attention to address water-related issues Gautam et al 2023).…”