Ensemble Boosting and Bagging Based Machine Learning Models for Groundwater Potential Prediction
- PDF / 1,249,757 Bytes
- 15 Pages / 439.37 x 666.142 pts Page_size
- 33 Downloads / 222 Views
Ensemble Boosting and Bagging Based Machine Learning Models for Groundwater Potential Prediction Amirhosein Mosavi 1,2 & Farzaneh Sajedi Hosseini 3 & Bahram Choubin 4 & Massoud Goodarzi 5 & Adrienn A. Dineva 6 & Elham Rafiei Sardooi 7 Received: 22 June 2020 / Accepted: 28 October 2020/ # Springer Nature B.V. 2020
Abstract
Due to the rapidly increasing demand for groundwater, as one of the principal freshwater resources, there is an urge to advance novel prediction systems to more accurately estimate the groundwater potential for an informed groundwater resource management. Ensemble machine learning methods are generally reported to produce more accurate results. However, proposing the novel ensemble models along with running comparative studies for performance evaluation of these models would be equally essential to precisely identify the suitable methods. Thus, the current study is designed to provide knowledge on the performance of the four ensemble models i.e., Boosted generalized additive model (GamBoost), adaptive Boosting classification trees (AdaBoost), Bagged classification and regression trees (Bagged CART), and random forest (RF). To build the models, 339 groundwater resources’ locations and the spatial groundwater potential conditioning factors were used. Thereafter, the recursive feature elimination (RFE) method was applied to identify the key features. The RFE specified that the best number of features for groundwater potential modeling was 12 variables among 15 (with a mean Accuracy of about 0.84). The modeling results indicated that the Bagging models (i.e., RF and Bagged CART) had a higher performance than the Boosting models (i.e., AdaBoost and GamBoost). Overall, the RF model outperformed the other models (with accuracy = 0.86, Kappa = 0.67, Precision = 0.85, and Recall = 0.91). Also, the topographic position index’s predictive variables, valley depth, drainage density, elevation, and distance from stream had the highest contribution in the modeling process. Groundwater potential maps predicted in this study can help water resources managers and policymakers in the fields of watershed and aquifer management to preserve an optimal exploit from this important freshwater. Keywords Groundwaterpotential prediction . Ensemblemachine learningmodels . Decisiontree . Boosting . Bagging . Recursive feature elimination
* Adrienn A. Dineva [email protected] Extended author information available on the last page of the article
A. Mosavi et al.
1 Introduction Todays, particularly in arid regions, there is an urge in groundwater potential modeling, as the scarcity of secure freshwater is a distinguished problem, where the spread of operations of irrigation, industry, and urbanism is almost associated with groundwater (Kordestani et al. 2019; Naghibi et al. 2019; Miraki et al. 2019). The traditional time consuming and expensive approaches to groundwater exploration, e.g., drilling and geological and geophysical practices, have been dramatically transformed by introducing geographic information sys
Data Loading...