Machine learning approaches for spatial modeling of agricultural droughts in the south-east region of Queensland Australia.

A quantitative understanding of the hydro-environmental factors that influence the occurrence of agricultural drought events would enable more strategic climate change adaptation and drought management plans. Practical drought hazard mapping remains challenging due to possible exclusion of the most pertinent drought drivers, and to the use of inadequate predictive models that cannot describe drought adequately. This research aims to develop new approaches to map agricultural drought hazard with state-of-the-art machine learning models, including classification and regression trees (CART), boosted regression trees (BRT), random forests (RF), multivariate adaptive regression splines (MARS), flexible discriminant analysis (FDA) and support vector machines (SVM). Hydro-environmental datasets were used to calculate the relative departure of soil moisture (RDSM) for eight severe droughts for drought-prone southeast Queensland, Australia, over the period 1994-2013. RDSM was then used to generate an agricultural drought inventory map. Eight hydro-environmental factors were used as potential predictors of drought. The goodness-of-fit and predictive performance of all models were evaluated using different threshold-dependent and threshold-independent methods, including the true skill statistic (TSS), Efficiency (E), F-score, and the area under the receiver operating characteristic curve (AUC-ROC). The RF model (AUC-ROC = 97.7%, TSS = 0.873, E = 0.929, F-score = 0.898) yielded the highest accuracy, while the FDA model (with AUC-ROC = 73.9%, TSS = 0.424, E = 0.719, F-score = 0.512) showed the worst performance. The plant available water holding capacity (PAWC), mean annual precipitation, and clay content were the most important variables to be used for predicting the agricultural drought. About 21.2% of the area is in high or very high drought risk classes, and therefore, warrant drought and environmental protection policies. Importantly, the models do not require data on the precipitation anomaly for any given drought year; the spatial patterns in AGH were consistent for all drought events, despite very different spatial patterns in precipitation anomaly among events. Such machine-learning approaches are able to construct an overall risk map, thus assisting in the adoption of a robust drought contingency planning measure not only for this area, but also, in other regions where drought presents a pressing challenge, including its influence on key practical dimensions of social, environmental and economic sustainability.

Capability and robustness of novel hybridized models used for drought hazard modeling in southeast Queensland, Australia.

Widespread detrimental and long-lasting droughts are having catastrophic impacts around the globe. Researchers, organizations, and policy makers need to work together to obtain precise information, enabling timely and accurate decision making to mitigate drought impacts. In this study, a spatial modeling approach based on an adaptive neuro-fuzzy inference system (ANFIS) and several metaheuristic optimizations (ANFIS-BA, ANFIS-GA, ANFIS-ICA, ANFIS-PSO) was developed to predict the spatial occurrence of drought in a region in southeastern Queensland, Australia. In this approach, data describing the distribution of eight drought-contributing factors were prepared for input into the models to serve as independent variables. Relative departures of rainfall (RDR) and relative departures of soil moisture (RDSM) were analyzed to identify locations where drought conditions have occurred. The set of locations in the study area identified as having experienced drought conditions was randomly divided into two groups, 70% were used for training and 30% for validation. The models employed these data to generate maps that predict the locations that would be expected to experience drought. The prediction accuracy of the model-produced drought maps was scrutinized with two evaluation metrics: area under the receiver operating characteristic curve (AUC) and root mean square error (RMSE). The results demonstrate that the hybridized models (ANFIS-BA (AUCmean = 83.7%, RMSEmean = 0.236), ANFIS-GA (AUCmean = 81.62%, RMSEmean = 0.247), ANFIS-ICA (AUCmean = 82.12%, RMSEmean = 0.247), and ANFIS-PSO (AUCmean = 81.42%, RMSEmean = 0.255)) yield better predictive performance than the standalone ANFIS model (AUCmean = 71.8%, RMSEmean = 0.344). Furthermore, sensitivity analyses indicated that plant-available water capacity, the percentage of soil comprised of sand, and mean annual precipitation were the most important predictors of drought hazard. The versatility of the new approach for spatial drought modeling and the capacity of ANFIS model hybridization to improve model performance suggests great potential to assist decision makers in their formulations of drought risk, recovery, and response management, and in the development of contingency plans.

PMT: New analytical framework for automated evaluation of geo-environmental modelling approaches.

Geospatial computation, data transformation to a relevant statistical software, and step-wise quantitative performance assessment can be cumbersome, especially when considering that the entire modelling procedure is repeatedly interrupted by several input/output steps, and the self-consistency and self-adaptive response to the modelled data and the features therein are lost while handling the data from different kinds of working environments. To date, an automated and a comprehensive validation system, which includes both the cutoff-dependent and -independent evaluation criteria for spatial modelling approaches, has not yet been developed for GIS based methodologies. This study, for the first time, aims to fill this gap by designing and evaluating a user-friendly model validation approach, denoted as Performance Measure Tool (PMT), and developed using freely available Python programming platform. The considered cutoff-dependent criteria include receiver operating characteristic (ROC) curve, success-rate curve (SRC) and prediction-rate curve (PRC), whereas cutoff-independent consist of twenty-one performance metrics such as efficiency, misclassification rate, false omission rate, F-score, threat score, odds ratio, etc. To test the robustness of the developed tool, we applied it to a wide variety of geo-environmental modelling approaches, especially in different countries, data, and spatial contexts around the world including, the USA (soil digital modelling), Australia (drought risk evaluation), Vietnam (landslide studies), Iran (flood studies), and Italy (gully erosion studies). The newly proposed PMT is demonstrated to be capable of analyzing a wide range of environmental modelling results, and provides inclusive performance evaluation metrics in a relatively short time and user-convenient framework whilst each of the metrics is used to address a particular aspect of the predictive model. Drawing on the inferences, a scenario-based protocol for model performance evaluation is suggested.