Application of rotation forest with decision trees as base classifier and a novel ensemble model in spatial modeling of groundwater potential Seyed Amir Naghibi & Mojtaba Dolatkordestani & Ashkan Rezaei & Payam Amouzegari & Mostafa Taheri Heravi & Bahareh Kalantar & Biswajeet Pradhan Received: 6 November 2018 /Accepted: 1 March 2019 # Springer Nature Switzerland AG 2019 Abstract Groundwater resources are facing a high pres- sure due to drought and overexploitation. The main aim of this research is to apply rotation forest (RTF) with decision trees as base classifiers and an improved ensem- ble methodology based on evidential belief function and tree-based models (EBFTM) for preparing groundwater potential maps (GPM). The performance of these new models is then compared with three previously imple- mented models, i.e., boosted regression tree (BRT), clas- sification and regression tree (CART), and random forest (RF). For this purpose, spring locations in the Meshgin Shahr in Iran were detected. The spring locations were randomly categorized into training (70% of the locations) and validation (30% of the locations) datasets. Further- more, several groundwater conditioning factors (GCFs) such as hydrogeological, topographical, and land use factors were mapped and regarded as input variables. The tree-based algorithms (i.e., BRT, CART, RF, and RTF) were applied by implementing the input variables and training dataset. The groundwater potential values (i.e., spring occurrence probability) obtained by the BRT, CART, RF, and RTF models for all the pixels of the study area were classified into four potential classes and then used as inputs of the EBF model to construct the new ensemble model (i.e., EBFTM). At last, this paper imple- mented a receiver operating characteristics (ROC) curve for determining the efficiency of the EBFTM, RTF, BRT, CART, and RF methods. The findings illustrated that the EBFTM had the highest efficacy with an area under the ROC curve (AUC) of 90.4%, followed by the RF, BRT, CART, and RTF models with AUC-ROC values of 90.1, 89.8, 86.9, and 86.2%, respectively. Thus, it could be inferred that the ensemble approach is capable of improv- ing the efficacy of the single tree-based models in GPM production. Environ Monit Assess (2019) 191:248 https://doi.org/10.1007/s10661-019-7362-y S. A. Naghibi (*) : P. Amouzegari Department of Watershed Management Engineering, Faculty of Natural Resources, Tarbiat Modares University (TMU), Noor, Mazandaran, Iran e-mail: Amirnaghibi2010@yahoo.com M. Dolatkordestani Jiroft University Scholarship, Department of Combat Desertification, College of Natural Resources, Jiroft University, Jiroft, Iran A. Rezaei Department of Range and Watershed Management, Faculty of Agriculture and Natural Resources Sciences, University of Hormozgan, Bandar Abbas, Iran M. T. Heravi Department of Civil Engineering, Eghbal Lahoori Institute of Higher Education, Khorasan Razavi, Mashhad, Iran B. Kalantar RIKEN Center for Advanced Intelligence Project, Goal-Oriented Technology Research Group, Disaster Resilience Science Team, Tokyo 103-0027, Japan B. Pradhan The Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and IT, University of Technology Sydney, Sydney, NSW 2007, Australia B. Pradhan Department of Energy and Mineral Resources Engineering, Choongmu-gwan, Sejong University, 209 Neungdong-ro, Gwangjin-gu, Seoul 05006, Korea