Decision-Tree-based data mining and rule induction for predicting and mapping soil bacterial diversity

Abstract

Soilmicrobial ecology plays a significant role in global ecosystems. Nevertheless, methods of model prediction and mapping have yet to be established for soil microbial ecology. The present study was undertaken to develop an artificial-intelligence- and geographical information system (GIS)-integrated framework for predicting and mapping soil bacterial diversity using pre-existing environmental geospatial database information, and to further evaluate the applicability of soil bacterial diversity mapping for planning construction of eco-friendly roads. Using a stratified random sampling, soil bacterial diversity was measured in 196 soil samples in a forest area where construction of an eco-friendly road was planned. Model accuracy, coherence analyses, and tree analysis were systematically performed, and four-class discretized decision tree (DT) with ordinary pair-wise partitioning (OPP) was selected as the optimal model among tested five DT model variants. GIS-based simulations of the optimal DT model with varying weights assigned to soil ecological quality showed that the inclusion of soil ecology in environmental components, which are considered in environmental impact assessment, significantly affects the spatial distributions of overall environmental quality values as well as the determination of an environmentally optimized road route. This work suggests a guideline to use systematic accuracy, coherence, and tree analyses in selecting an optimal DT model from multiple candidate model variants, and demonstrates the applicability of the OPP-improved DT integrated with GIS in rule induction for mapping bacterial diversity. These findings also provide implication on the significance of soil microbial ecology in environmental impact assessment and eco-friendly construction planning.

A data‐mining‐based approach for aeolian desertification susceptibility assessment: A case‐study from Northern China

“…Qi and Zhu () and Braun et al () pointed out that compared with ANN and NB algorithms, the DT has the advantages of easily comprehensible mining results and high accuracy. Furthermore, the ANN algorithm requires a specialist to determine network structure and set various parameters, which affects the efficacy of models to some extent (Kim et al, ; Pal & Mather, ). Also, Pal and Mather () indicated that the DT is more accurate than ANN in land‐cover classification.…”

Internet of Things and Machine Learning Applications for Smart Precision Agriculture

“…assisted decision tree and artificial neural network-based model for assessing the landscape-soil relationship in inaccessible areas of Thailand. Kim et al [99] established the decision-tree assisted model combined with the geographical information system for forecasting and mapping the variety of bacteria in the soil. Rossi Neto et al [100] elucidated a decision tree-based approach for categorising the biometric attributes with the highest impact on the sugarcane productivity under the distinct arrangement of plants and edaphoclimatic settings.…”

Decision Tree-Based Data Mining and Rule Induction for Identifying High Quality Groundwater Zones to Water Supply Management: a Novel Hybrid Use of Data Mining and GIS

“…The summary of tree-based data mining algorithms is presented in Table 1. These tree-based algorithms are frequently used in many fields and for different applications (Kim et al 2011;Rodriguez-Galiano et al 2012;Rahmati et al 2016;Yoo et al 2016;Belgiu and Drăguţ 2016;Hong et al 2016;Naghibi et al 2017;Heil et al 2017;Chen et al 2017;Robinson et al 2018;Rayaroth and Sivaradje 2019;Al-Juboori 2019). For specific detail on the theoretical bases of data mining, its algorithms, and application, the reader is referred to the works of Rokach and Maimon (2005), Han et al (2011), Liao et al (2012), Rokach and Maimon (2014).…”