A novel geographical information system-based Ant Miner algorithm model for delineating groundwater flowing artesian well boundary: a case study from Iraqi southern and western deserts

The Ant Miner algorithm was compared with the bivariate frequency ratio (FR) and boosted regression trees (BRT) algorithms in terms of its capacity to assess groundwater potential. A geospatial dataset was prepared that contains two components: a flowing well inventory map and eleven factors relevant to groundwater conditions. Average nearest neighbor technique was used to investigate the spatial pattern of flowing wells and to find the appropriate distance between flowing and nonflowing points in the study area. A wrapper approach known as random forest classifier and a filtering approach known as information gain ratio were used to identify the most relevant groundwater factors. The developed models were validated via the area under the operating characteristic curve. Results revealed that the Ant Miner model performed better in terms of both success (0.944) and prediction (0.92) rates compared to FR and BRT. Furthermore, the Ant Miner algorithm derived five simple, easily interpreted rules for predicting groundwater potential that can be used by hydrogeologists for identifying potential groundwater well locations with minimal effort and cost.     

Evaluating the Dibdibba Aquifer Productivity at the Karbala–Najaf Plateau (Central Iraq) Using GIS-Based Tree Machine Learning Algorithms

Natural Resources Research - This study assessed the groundwater productivity of the Dibdibba aquifer on the Karbala–Najaf Plateau, central Iraq, using three GIS-based tree machine learning...     

Flowing well potential zoning at Iraqi southern and western deserts using frequency ratio and geographic information system

The objective of this study is to integrate geographic information system and bivariate frequency ratio method for the mapping of flowing well zones in the west and southwest parts of the Euphrates river basin of Iraq. Ten groundwater conditioning factors are identified as controlling factors of groundwater movement based on data availability, literature review, and expert’s opinions. The spatial association between flowing well locations and groundwater controlling factors is investigated by means of a probabilistic frequency ratio approach. Seventy percent or 148 wells from an inventory of 211 flowing wells in the study area are randomly selected for training, and the remaining 30 or 63% wells are used for validation of the probabilistic frequency ratio model. The estimated probabilistic ratio values are overlaid and summed to produce the groundwater potential index map. The results reveal that groundwater potential in 128,547 km² or 84% of the total area is very low to low. The moderate potential zone covers an area of about 11,210 km² or 7%, while the high and very high potential zones are found in an area of 12,982 km² or 9% of the study area. Validation of obtaining results by means of a receiver operating characteristic technique reveals that the predictive accuracy of 94% indicating the excellent performance of the proposed approach for spatial zoning of groundwater flowing well boundary at Iraqi desert.     

Mapping flood susceptibility in an arid region of southern Iraq using ensemble machine learning classifiers: a comparative study

This study examined the efficacy of three machine ensemble classifiers, namely, random forest, rotation forest and AdaBoost, in assessing flood susceptibility in an arid region of southern Iraq. A dataset was created from flooded and non-flooded areas to train and validate the ensemble classifiers using a binary classification scheme (1—flood, 0—non-flood). The prepared dataset was then partitioned into two sets with a 70/30 ratio: 70% (2478 pixels) for training and 30% (1062 pixels) for testing. A total of 10 influential flood factors were selected and prepared based on data availability and a literature review. The selected factors were surface elevation, slope, plain curvature, topographic wetness index, stream power index, distance to rivers, drainage density, lithology, soil and land use/land cover. The information gain ratio was first utilised to explore the predictive abilities of the factors. The predictive performances of the three ensemble models were compared using six statistical measures: sensitivity, specificity, accuracy, kappa, root mean square error and area under the operating characteristics curve. The results revealed that the AdaBoost classifier was the best in terms of the statistical measures, followed by the random forest and rotation forest models. A flood susceptibility map was prepared based on the result of each classifier and classified into five zones: very low, low, moderate, high and very high. For the model with the best performance, i.e., the AdaBoost model, these zones were distributed over an area of 6002 km² (44%) for the very low–low zone, 2477 km² (18%) for the moderate zone and 5048 km² (40%) for the high–very high zones. This study proved the high capabilities of ensemble machine learning classifiers to decipher flood susceptibility zones in an arid region.     

Susceptibility mapping of gully erosion using GIS-based statistical bivariate models: a case study from Ali Al-Gharbi District,Maysan Governorate,southern Iraq

This work aims to evaluate the predictive capability of three bivariate statistical models, namely information value, frequency ratio, and evidential belief functions, in gully erosion susceptibility mapping in northeastern Maysan Governorate (Ali Al-Gharbi District) in southern Iraq. The gully inventory map, consisting of 21 gullies of different sizes, was prepared based on the interpretation of remotely sensed data supported by field survey. The gully inventory data (polygon format) were randomly partitioned into two sets: 14 gullies for build and training the bivariate model, and the remaining 7 gullies for validating purposes. Twelve gully influential factors were selected based on data availability and the literature review. The selected factors were related to lithology, geomorphology, soil, land cover, and topography (primary and secondary) settings. Analysis of factor importance using information gain ratio proved that out of 12 gully influential factors, eight were of more importance in developing gullies (the average merit was greater than zero). The most important factors and the training gully inventory map were used to generate three gully erosion susceptibility maps based on the three bivariate models used. For validation, the area under the operating characteristics curves for both success and prediction rates was used. The results indicated that the highest prediction rate of 82.9% was achieved using the information value technique. All the bivariate models had prediction rates greater than 80%, and thus they were regarded as very good estimators. The final conclusion was that the bivariate models offer advanced techniques for mapping gully erosion susceptibility.