Automated Analysis of the US Drought Monitor Maps With Machine Learning and Multiple Drought Indicators

Abstract

The US Drought Monitor (USDM) is a hallmark in real time drought monitoring and assessment as it was developed by multiple agencies to provide an accurate and timely assessment of drought conditions in the US on a weekly basis. The map is built based on multiple physical indicators as well as reported observations from local contributors before human analysts combine the information and produce the drought map using their best judgement. Since human subjectivity is included in the production of the USDM maps, it is not an entirely clear quantitative procedure for other entities to reproduce the maps. In this study, we developed a framework to automatically generate the maps through a machine learning approach by predicting the drought categories across the domain of study. A persistence model served as the baseline model for comparison in the framework. Three machine learning algorithms, logistic regression, random forests, and support vector machines, with four different groups of input data, which formed an overall of 12 different configurations, were used for the prediction of drought categories. Finally, all the configurations were evaluated against the baseline model to select the best performing option. The results showed that our proposed framework could reproduce the drought maps to a near-perfect level with the support vector machines algorithm and the group 4 data. The rest of the findings of this study can be highlighted as: 1) employing the past week drought data as a predictor in the models played an important role in achieving high prediction scores, 2) the nonlinear models, random forest, and support vector machines had a better overall performance compared to the logistic regression models, and 3) with borrowing the neighboring grid cells information, we could compensate the lack of training data in the grid cells with insufficient historical USDM data particularly for extreme and exceptional drought conditions.

Nature-based Solutions for Urban Resilience and Human Health

“…Following previous studies (Sun Yu et al, 2020;Shah et al, 2021;Tan et al, 2021), four dominant factors, namely normalized difference vegetation index (P_NDVI), land surface temperature (P_LST), shape index (P_SI) and area (P_Area) of UGS patches were selected to explore their influence on the cooling intensity and range of UGS. The shape index represents the complexity of patch shape.…”

“…found that the TVoE was about 0.6-0.62 ha in Hong Kong, Jakarta, Mumbai, and Singapore, and 0.92-0.96 ha in Kaohsiung, Kuala Lumpur, and Taiwan. Tan et al (2021) found that the TVoE of three-based green spaces was about 0.31 ha in Nanning, China. The TVoE was found to be 4.55 ha in Fuzhou (Yu, et al, 2017).…”

“…First, it does not require feature scaling or transformation, and can handle independent variables with different scales and units, allowing for more convenient and efficient processing of multi-dimensional data (Mishra et al, 2020). Additionally, the RFR model can capture nonlinear relationships between independent variables and the target variable (Fan et al, 2023), including nonlinear relationships and higher-order interactions, making it suitable for modeling complex relationships (Hatami Bahman Beiglou et al, 2021). Specifically, the RFR model has significant advantages in quantifying the threshold sizes of different landscape types (while accounting for the effects of landscape composition and configuration) to optimize the cooling efficiency of blue-green spaces.…”

“…To quantify the cooling effect of UGS, Yu et al (2017) defined the intensity, range and efficiency of urban cooling island (UCI), as well as the threshold value of efficiency (TVoE). The TVoE has been used to acquire the most suitable patch size of urban green space in different study areas Yang et al, 2020;Tan et al, 2021). Numerous evidences from field observations and remote sensing data proved that the cooling intensity and range of parks have a positive relationship with their areas (Lin et al, 2015;Vaz Monteiro, 2016).…”