|
Our new paper entitled, "Simulating flood risk in Tampa Bay using a machine learning driven approach" is published in npj: Natural Hazards. Below is the abstract: "Machine learning (ML) models can simulate flood risk by identifying critical non-linear relationships between flood damage locations and flood risk factors (FRFs). To explore it, Tampa Bay, Florida, is selected as a test site. The study’s goal is to simulate flood risk and identify dominant FRFs using historical flood damage data as target variable, with 16 FRFs as predictor variables. Five different ML models such as decision tree (DT), support vector machine (SVM), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and random forest (RF) were adopted. RF classifies 2.42% of Tampa Bay as very high risk and 2.54% as high risk, while XGBoost classifies 3.85% as very high risk and 1.11% as high risk. Moreover, the communities reside at low altitudes and near the waterbodies, with dense man-made infrastructure, are at high flood risk. This study introduces a comprehensive framework for flood risk assessment and helps policymakers mitigate flood risk."
3 Comments
9/18/2024 0 Comments My new analysis article In my analysis article published in the Conversation, I argue that the increasing damages caused by hurricanes are partly due to climate change effects and partly due to growing coastal population.
"Warm water in the Atlantic Ocean and Gulf of Mexico can fuel powerful hurricanes, but how destructive a storm becomes isn’t just about the climate and weather – it also depends on the people and property in harm’s way. In many coastal cities, fast population growth has left more people living in areas at high risk of flooding." In a new paper that is published in Natural Hazards, we applied multiple algorithms to model flood susceptibility in New Orleans. Please find the abstract below: "Machine learning (ML) models, particularly decision tree (DT)-based algorithms, are being increasingly utilized for flood susceptibility mapping. To evaluate the advantages of DT-based ML models over traditional statistical models on flood susceptibility assessment, a comparative study is needed to systematically compare the performances of DT- based ML models with that of traditional statistical models. New Orleans, which has a long history of flooding and is highly susceptible to flooding, is selected as the test bed. The primary purpose of this study is to compare the performance of multiple DT-based ML models namely DT, Adaptive Boosting (AdaBoost), Gradient Boosting (GdBoost), Extreme Gradient Boosting (XGBoost) and Random Forest (RF) models with a traditional statistical model known as Frequency Ratio (FR) model in New Orleans. This study also aims to identify the main drivers contributing to flooding in New Orleans using the best performing model. Based on the most recent Hurricane Ida-induced flood inventory map and nine crucial flood conditioning factors, the models’ accuracies are tested and compared using multiple evaluation metrics. The findings of this study indicate that all DT-based ML models perform better compared to FR. The RF model emerges as the best model (AUC = 0.85) among all DT-based ML models in every evaluation metrics. This study then adopts the RF model to simulate flood susceptibility map (FSM) of New Orleans and compares it with the prediction of FR model. The RF model also demonstrates that low elevation and higher precipitation are the main factors responsible for flooding in New Orleans. Therefore, this comparative approach offers a significant understanding about the advantages of advanced ML models over traditional statistical models in local flood susceptibility assessment."  Our new paper using a mixed methods approach to understanding public perceptions of groundwater management in Baton Rouge was published on Frontier in Water. Below is the abstract:
"In Louisiana's Capital Area Groundwater Conservation District (CAGWCD), extensive groundwater withdrawals from the Southern Hills Aquifer System have begun to accelerate the infiltration of saltwater into the aquifer's freshwater sands. This accelerated saltwater intrusion has the potential to reduce the amount of groundwater available for public consumption and other industrial and agricultural uses throughout the region. In response to this threat, the Capital Area Ground Water Conservation Commission has begun development of a long-term strategic plan to achieve and maintain sustainable and resilient groundwater withdrawals from the aquifer system. The development of the strategic plan includes an assessment of public attitudes regarding groundwater and groundwater management in the CAGWCD. This paper presents the results of mixed methods public participatory research to evaluate current and historical views and attitudes around groundwater quality, quantity, and cost in the CAGWCD. The mixed methods approach used in this research employed a sequential explanatory design model consisting of two phases. The first phase involved the implementation of an internet-based survey, followed by a qualitative phase aimed at explaining and enhancing the quantitative results. The qualitative phase employed a combination of one-on-one interviews and focus groups. The research found that the primary governance obstacle that decision-makers may face in managing groundwater is a broad lack of public awareness of groundwater and groundwater issues in the CAGWCD. Despite the criticality of over-pumping and saltwater intrusion into the aquifer system, survey research and subsequent interviews and focus groups have shown that the public is largely unaware of these issues. This research also found a general lack of trust in both industry and government to manage groundwater issues and highlighted the need for groundwater management efforts to be led by unbiased, trusted institutions." |
|
RSS Feed