Department of Soils and Agri-Food Engineering, Laval University, Québec G1V0A6, Canada.
Department of Soils and Agri-Food Engineering, Laval University, Québec G1V0A6, Canada.
Sci Total Environ. 2020 Jun 25;723:138015. doi: 10.1016/j.scitotenv.2020.138015. Epub 2020 Mar 17.
Endorheic lakes are one of the most important factors of an environment. Regarding their morphology, these lakes, in particular saline lakes, are much more sensitive and can either benefit or pose a threat to their surroundings. Thus, constant monitoring of such lakes' water level, modeling and analyzing them for future planning and management policies is vitally important. We proposed a generalized linear stochastic model (GLSM) for forecasting the weekly and monthly Urmia lake water levels, the sixth-largest saltwater lake on Earth. In this methodology, three approaches are defined to pre-process data. The first approach is merely based on the differencing method, while the second and third are a one-step (the combination of de-trending with standardization and spectral analysis) and two-step (the combination of the 2nd approach with normalization transform) preprocessing, respectively. A thorough comparison of the GLSM results with eminence nonlinear AI models (Adaptive Neuro-Fuzzy Inference Systems, ANFIS, Multilayer Perceptron, MLP, Gene Expression Programming, GEP, Support Vector Machine with Firefly algorithm, SVM-FFA, and Artificial Neural Networks ANN) showed that by using an appropriate method that delivers accurate information of the entailing terms in time series, it is possible to model Urmia lake level with acceptable precision. Concisely, the GSLM with coefficients of determination (R) 99.957% and root mean squared error (RMSE) of 2.121% outperformed the SVM-FFA with R 99.59%, RMSE 3.27%, ANN with R 99.56%, RMSE 3.3%, ANFIS with R 98.9%, RMSE 4.3%, GP with R 99.89%, RMSE 3.47%, GEP with R 94.75%, RMSE 4.15% for forecasting weekly time series. In forecasting monthly time series, the GLSM method with R 99.517% and RMSE 6.91% also outperformed GEP R 91.95%, RMSE 15.3%, ANFIS R 92.85%, RMSE 47.55% models. Consequently, GSLM proved that by applying proper comprehensible linear techniques promising results can be obtained rather than using sophisticated AI methods.
内陆湖是环境的重要因素之一。就其形态而言，这些湖泊，特别是咸水湖，更加敏感，可以造福于周围环境，也可以对其构成威胁。因此，持续监测这些湖泊的水位，对其进行建模和分析，以制定未来的规划和管理政策，至关重要。我们提出了一种广义线性随机模型（GLSM），用于预测地球上第六大盐水湖乌鲁米耶湖的每周和每月水位。在这种方法中，定义了三种方法来对数据进行预处理。第一种方法仅仅基于差分法，而第二种和第三种方法分别是一步法（去趋势标准化和光谱分析的组合）和两步法（第二种方法与归一化变换的组合）。将 GLSM 结果与杰出的非线性人工智能模型（自适应神经模糊推理系统（ANFIS）、多层感知器（MLP）、基因表达编程（GEP）、支持向量机与萤火虫算法（SVM-FFA）和人工神经网络（ANN））进行了彻底比较，结果表明，通过使用一种能够及时提供时间序列中蕴含术语的准确信息的适当方法，可以以可接受的精度对乌鲁米耶湖水位进行建模。简而言之，广义线性随机模型的决定系数（R）为 99.957%，均方根误差（RMSE）为 2.121%，优于萤火虫算法支持向量机的 R 为 99.59%，RMSE 为 3.27%，人工神经网络的 R 为 99.56%，RMSE 为 3.3%，自适应神经模糊推理系统的 R 为 98.9%，RMSE 为 4.3%，基因表达式编程的 R 为 99.89%，RMSE 为 3.47%，广义预测模型的 R 为 94.75%，RMSE 为 4.15%，用于预测每周时间序列。在预测每月时间序列时，广义线性随机模型的 R 为 99.517%，RMSE 为 6.91%，也优于基因表达式编程的 R 为 91.95%，RMSE 为 15.3%，自适应神经模糊推理系统的 R 为 92.85%，RMSE 为 47.55%。因此，广义线性随机模型证明，通过应用适当的、易于理解的线性技术，可以获得有希望的结果，而不必使用复杂的人工智能方法。
