Search results

The purpose of the paper is to predict mapping of areas vulnerable to flooding in the Ourika watershed in the High Atlas of Morocco with the aim of providing a useful tool capable of helping in the mitigation and management of floods in the associated region, as well as Morocco as a whole.

Four machine learning (ML) algorithms including k-nearest neighbors (KNN), artificial neural network, random forest (RF) and x-gradient boost (XGB) are adopted for modeling. Additionally, 16 predictors divided into categorical and numerical variables are used as inputs for modeling.

The results showed that RF and XGB were the best performing algorithms, with AUC scores of 99.1 and 99.2%, respectively. Conversely, KNN had the lowest predictive power, scoring 94.4%. Overall, the algorithms predicted that over 60% of the watershed was in the very low flood risk class, while the high flood risk class accounted for less than 15% of the area.

There are limited, if not non-existent studies on modeling using AI tools including ML in the region in predictive modeling of flooding, making this study intriguing.

The purpose of this paper is to identify vulnerable areas for flood hazard and to analyze stakes exposed in touristic valley of Morrocan mountains. The three goals are: methodological (low-cost diagnosis without starting data), operational (to show the risk and identify avenues of prevention in Ourika) and incentive (to reproduce this on other sectors in Morocco).

The vulnerability of three areas of the Ourika valley (the most frequented) was assessed by a hydro-geomorphological study, human frequentation surveys and risk indices at the building scale.

Surveys carried out in the field allowed the identification of areas with high risk, the evaluation of the buildings’ vulnerability and the frequentation of the valley. Evacuation plans, allowing easy access to potential refuges in case of flood, were finally proposed.

The reproducible, inexpensive and relevant nature of the approach (integrated and spatialized) helps in decision making and facilitating dialogue for prevention.

The purpose of this study is to assess how intergovernmental panel on climate change’s (IPCC’s) sixth assessment report of Working Group I (WGI), a Summary for Policymakers (SPM), has evaluated the current climate change situation. The author uses the qualitative content analysis (QCA) method (i.e. summative content analysis [SCA]) to identify critical points of the SPM.

To better understand the WGI report and its SPM, the author uses the thematic analysis, often called the QCA method. This study takes more steps and uses one of the main qualitative content analysis approaches (i.e. SCA). Therefore, QCA (SCA) can help the author count the occurrence of certain words using computer-assisted qualitative data analysis software that quantifies the words in the data. This process helps the author to understand codes and patterns (e.g. the concept in the results section).

Interestingly, the AR6 says more about adaptation for policy makers in sections C (Climate information for risk assessment) and D (Mitigation of future climate change) than in sections A and D. Finally, this study concludes that the IPCC WGI SPM has addressed evidence on global climate change policymaking for SPMa, SPMd (mitigation-based strategies and mitigation policy [MP]) and SPMb, SPMc (adaptation policy and adaptation-based strategy).

First, this study refers only to the contribution of WGI, a SPM. The findings of this study do not necessarily provide a full understanding of what the AR6 WGI SPM says about climate change. It points out that the QDA Miner software and Voyant tool do not include all variables and examples where mitigation and adaptation-based strategies are discussed. The guidance for coding is based on the approved version of IPCC AR6 WGI SPM. The final limitation is that the relatedness of key words (e.g. confidence, high and warming) is sometimes ambiguous; even experts may disagree on how the words are linked to form a concept. Thus, this method works at the keyword level. A more intelligent method would use more meaningful information than keywords.

This study used qualitative data analysis (SCA) to explore what was said about climate change in four sections of the IPCC AR6 WGI SPM, which may influence current and future global climate change policymaking.