Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS), University of Technology Sydney, NSW, 2007, Australia.
Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS), University of Technology Sydney, NSW, 2007, Australia; Department of Energy and Mineral Resources Engineering, Sejong University, Choongmu-gwan, 209 Neungdong-ro, Gwangjin-gu, Seoul, 05006, South Korea; Center of Excellence for Climate Change Research, King Abdulaziz University, P. O. Box 80234, Jeddah, 21589, Saudi Arabia; Earth Observation Center, Institute of Climate Change, Universiti Kebangsaan Malaysia, 43600, UKM, Bangi, Selangor, Malaysia.
J Environ Manage. 2021 Apr 1;283:111979. doi: 10.1016/j.jenvman.2021.111979. Epub 2021 Jan 19.
Droughts are slow-moving natural hazards that gradually spread over large areas and capable of extending to continental scales, leading to severe socio-economic damage. A key challenge is developing accurate drought forecast model and understanding a models' capability to examine different drought characteristics. Traditionally, forecasting techniques have used various time-series approaches and machine learning models. However, the use of deep learning methods have not been tested extensively despite its potential to improve our understanding of drought characteristics. The present study uses a deep learning approach, specifically the Long Short-Term Memory (LSTM) to predict a commonly used drought measure, the Standard Precipitation Evaporation Index (SPEI) at two different time scales (SPEI 1, SPEI 3). The model was compared with other common machine learning method, Random Forests, Artificial Neural Networks and applied over the New South Wales (NSW) region of Australia, using hydro-meteorological variables as predictors. The drought index and predictor data were collected from the Climatic Research Unit (CRU) dataset spanning from 1901 to 2018. We analysed the LSTM forecasted results in terms of several drought characteristics (drought intensity, drought category, or spatial variation) to better understand how drought forecasting was improved. Evaluation of the drought intensity forecasting capabilities of the model were based on three different statistical metrics, Coefficient of Determination (R), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). The model achieved R value of more than 0.99 for both SPEI 1 and SPEI 3 cases. The variation in drought category forecasted results were studied using a multi-class Receiver Operating Characteristic based Area under Curves (ROC-AUC) approach. The analysis revealed an AUC value of 0.83 and 0.82 for SPEI 1 and SPEI 3 respectively. The spatial variation between observed and forecasted values were analysed for the summer months of 2016-2018. The findings from the study show an improvement relative to machine learning models for a lead time of 1 month in terms of different drought characteristics. The results from this work can be used for drought mitigation purposes and different models need to be tested to further enhance our capabilities.
干旱是一种缓慢移动的自然灾害，逐渐蔓延到广大地区，并能扩展到大陆尺度，导致严重的社会经济损失。一个关键的挑战是开发准确的干旱预测模型，并了解模型检查不同干旱特征的能力。传统上，预测技术使用了各种时间序列方法和机器学习模型。然而，尽管深度学习方法有潜力提高我们对干旱特征的理解，但尚未广泛测试其在预测中的应用。本研究使用深度学习方法，特别是长短期记忆（LSTM），来预测常用的干旱指标之一，即标准降水蒸发指数（SPEI）在两个不同的时间尺度（SPEI1、SPEI3）上的情况。该模型与其他常见的机器学习方法，如随机森林、人工神经网络进行了比较，并应用于澳大利亚新南威尔士州（NSW）地区，使用水文气象变量作为预测因子。干旱指数和预测因子数据来自气候研究单位（CRU）数据集，时间跨度为 1901 年至 2018 年。我们根据几个干旱特征（干旱强度、干旱类别或空间变化）分析了 LSTM 预测结果，以更好地了解干旱预测是如何得到改善的。模型对干旱强度预测能力的评估基于三个不同的统计指标，即决定系数（R）、均方根误差（RMSE）和平均绝对误差（MAE）。对于 SPEI1 和 SPEI3 情况，模型的 R 值均超过 0.99。使用基于多类接收器操作特征的曲线下面积（ROC-AUC）的方法研究了干旱类别预测结果的变化。分析结果表明，SPEI1 和 SPEI3 的 AUC 值分别为 0.83 和 0.82。分析了 2016 年至 2018 年夏季观测值和预测值之间的空间变化。研究结果表明，与机器学习模型相比，在 1 个月的提前期内，不同干旱特征的预测结果有所改善。这项工作的结果可用于干旱缓解目的，需要进一步测试不同的模型来提高我们的能力。
