由 张 良承 A Combined Model to Predict GNSS Precipitable Water Vapor Based on Deep Learning
基于深度学习的GNSS大气可降水量预测融合模型研究
引文格式 | Citation:
SHANGGUAN M, DANG M, YUE Y, et al. A Combined Model to Predict GNSS Precipitable Water Vapor Based on Deep Learning[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023, 16: 4713-4723. DOI:10.1109/JSTARS.2023.3278381.
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing（中科院2区，IF：5.3）
Combined model
global navigation satellite system (GNSS)
neural networks
precipitable water vapor (PWV) prediction
global navigation satellite system (GNSS)
neural networks
precipitable water vapor (PWV) prediction
Abstract | 摘要
The precipitable water vapor (PWV) is a key parameter to reflect atmospheric water vapor, which can be derived by the global navigation satellite system (GNSS) technique with high accuracy and temporal resolution. PWV is an important parameter for weather forecasts and climate research. To develop a highly accurate PWV prediction model, we first combine the wavelet analysis (Wa), long short-term memory (LSTM) neural network, and autoregressive integrated moving average (ARIMA) algorithms as WLA model for the GNSS PWV prediction. Wa, LSTM, and ARIMA in WLA separate the random noise and predict the nonlinear and linear trends in PWV, respectively. Afterward, the WLA model is compared with LSTM, ARIMA, wavelet neural networks, and the multivariable linear regression (MLR) method. The WLA model shows the best result in the five prediction models in terms of the root-mean-square error (RMSE, 0.19–0.82 mm) and mean absolute error (0.01–0.07), which are 55.48% and 55.32% lower than other models, and Nash–Sutcliffe efficiency coefficient (NSE, 76.53%–99.7%) is 9.42% greater than other models. For further analysis, we also study the WLA performance in different months using one-month’s data as training length. The result shows that WLA has good effects in predicting PWV in different months and the average NSE of WLA is 95%. In addition, the predicted PWV of the WLA model within 3 h is found to be accurate and reliable (RMSE < 2 mm, relative error < 0.1, NSE > 60%). This study demonstrates the good performance of WLA to predict GNSS PWV.
大气可降水量（PWV）是反映大气水汽含量的关键参数，利用全球导航卫星系统（GNSS）技术可反演得到高精度、高时间分辨率的PWV数据，其为天气预报与气候研究提供了重要支撑。为建立高精度PWV预测模型，本研究首次联合小波分析（Wa）、长短期记忆（LSTM）神经网络与自回归积分滑动平均（ARIMA）算法，构建了用于GNSS PWV预测的WLA组合模型。该模型中，Wa、LSTM和ARIMA分别用于分离随机噪声、预测PWV的非线性趋势与线性趋势。进一步将WLA模型与LSTM、ARIMA、小波神经网络以及多元线性回归（MLR）方法进行比较。结果表明，WLA在五种预测模型中表现最优，其均方根误差（RMSE，0.19–0.82 mm）和平均绝对误差（MAE，0.01–0.07 mm）较其他模型平均降低55.48%和55.32%，纳什-效率系数（NSE，76.53%–99.7%）平均提高9.42%。为深入分析，本研究还以一个月数据作为训练长度，评估了WLA模型在不同月份中的预测表现，结果显示WLA在各月中均具有良好的预测效果，平均NSE达到95%。此外，WLA模型在3小时内的PWV预测结果准确可靠（RMSE < 2 mm，相对误差 < 0.1，NSE > 60%）。本研究证明了WLA模型在GNSS PWV预测中具有良好的性能。