Link Search Menu Expand Document
AIEE

Deep learning of S/T interpolation, CMAQ and WRF

Table of contents

背景

資訊科學基本

  • 有關卷積
    • wiki

      在泛函分析中，捲積（又稱疊積（convolution）、褶積或旋積），是透過兩個函數 f 和 g 生成第三個函數的一種數學算子，表徵函數 f 與經過翻轉和平移的 g 的乘積函數所圍成的曲邊梯形的面積。如果將參加摺積的一個函數看作區間的指示函數，摺積還可以被看作是「滑動平均」的推廣。

  • 數位中介法沒有屏蔽的 AI 大數據大補帖 系列 第 3 篇 - Day3 深度學習基本名詞介紹阿柴2023
  • 如何通俗易懂地解释卷积？知乎2022

環工上的應用

Spatial/Temporal interpolation with machine learning

sourcesapplicationsmethods 
Li et al., (2011)1mud content samples in the southwest Australian margin spatial interpolationRF 23 methods 
Zhang et al(2017)2crowd flow predictionST-ResNet 
Dixon et al., (2018)3traffic volume and speedDynamic Spatio-Temporal Modeling 
Helber et al., (2019)4landuse interpolation and fusiondeep convolutional neural networks 
Le et al., (2019)5SeoulConvLSTM 
Abirami and Chitra (2021)6AQ in DelhiSTAA-LSTM 
Shi and Wang(2021)7cone pressure/soundingensemble radial basis function network (RBFN) 
Kiessling(2021)windAdaptive Random Fourier, NN, RF 
Leirvik and Yuan, (2021)8solar radiation S/T interpolationRF and other 7 models 
Rendyk (2021)Evapotransporation, TemperatureIDW, NN, Thin Plate Spline Regression, GAM, Triangulated Irregular Network, Ordinary Kriging, AutoKriging, Co-Kriging 
Wang et al., (2021)9rainfall S/T interpolationdeep learning regression models 
Melker Hoglund (2022)10wind monitor sites interpolationneural network, random forest 
Hengl et al. (2022)11temp at sitesEnsemble Machine Learning 
Kirkwood et al.(2022)12remote sensing interpolationBayesian Deep Learning 
Kim et al., (2022)13Korean House PricesNN, RF, IDW, and Kriging 
Brecht et al(2022)wind and traj.NN 
Zhou et al 2022Frost PredictionANN 
Zhang et al., (2022)14PM2.5Deep Geometric Spatial Interpolation 
Elbaz et al., 202315Noem HRAResNet+ConvLSTM 
Oliveira Santos et al., (2023)16Houstonozone predictionGCNN, GraphSAGE

CMAQ and AI’s

作者年代地區應用方法
Friberg et al., 201617GeorgiaHRACMAQ+weightted variance
Lyu et al., 201918中國NRT analysisCMAQ+ensemble deep learning
Eslami, 202019德州空品預報CMAQ+CNN+EnKF
O’Neill et al., 202120加州森林火災CMAQ+datafusion
Sayeed et al., 202121南韓AQ forecastingCMAQ+deep CNN
Sun et al., 202122Bay AreaAQ forecastingCMAQ+LSTM
Dharmalingam et al., 202223AtlantaHRACMAQ+RF
Ren et al., 202224美陸空品變遷CMAQ+BEML
Hong et al., 202225釜山local scale predictionsCMAQ+RNN+LSTM
Huang et al., 202226北卡source apportionmentCMAQ + datafusion + CMBGC-Iteration
Jang et al., 202227釜山hr PM2.5 predictionsCMAQ+datafusion
Huang et al., 202328京津冀emission adjustments and AQ forecastingnudging+exRT

AIoT and Data Fusion

  • Lin, Y.-C., Chi, W.-J., Lin, Y.-Q. (2020). The improvement of spatial-temporal resolution of PM2.5 estimation based on micro-air quality sensors by using data fusion technique. Environment International 134, 105305. doi
    • 本研究開發一套針對空氣細懸浮微粒(PM2.5)擴散時空機制萃取的研究流程，並以台灣中部地區2010至2018年空污季節(10月至隔年3月)資料作為此研究架構之示範，探討在污染日(環保署定義之PM2.5日均值大於35μg/m3)發生時，PM2.5的擴散特徵。
    • 首先建構創新多感測器時空資料融合技術，整合時空異質性資料(於本研究為空氣盒子及環保署測站資料)以提升推估PM2.5濃度分布之時空解析度。
    • 此技術藉由最佳線性數據融合理論搭配克利金空間推估法(Kriging)，計算監測資料之日變動程度及空間推估時產生之可能誤差作為將資料線性融合時的權重。
    • 研究結果顯示透過資料融合技術能夠更合理地推估PM2.5濃度時空分布；接著，本研究首創以地表觀測資料所驅動的PM2.5擴散特徵萃取技術，而此階段技術首先利用移動平均及區域極值之計算找出PM2.5於污染日中濃度開始累積的時間點(Local minima)，針對這些時間點以小波訊號分析(Continuous wavelet transform, CWT)搭配主成分分析法(Principal component analysis, PCA)萃取出PM2.5在日尺度天氣變化影響下於研究區域主要的擴散行為。
    • CWT運作方式為拆解原始時間序列將其表示為數個頻率組合的函數，而透過小波訊號相關方法中之交叉小波分析(Cross wavelet transform, XWT)能夠計算兩訊號(兩測站監測之PM2.5濃度時間序列)在各頻段於不同時間的相關性以及其相位角之差異，相位差在空間分布上可顯示PM2.5在不同測站間傳遞的延遲時間，將XWT分析之PM2.5傳遞延遲時間於空間分布上推估之結果定為污染物擴散的空間分布情況，最後將所有污染日之擴散情況藉由PCA將巨量資料作線性降維與特徵萃取，運作上將時空變數拆解成多個時間與空間的變數成乘積之線性疊加，以此得到PM2.5在時間與空間上的主要變動特徵，意即得到研究區域(中部地區)主要的PM2.5擴散行為。
    • 研究結果發現中部地區約有六種主要擴散特徵(Principal components, PC1~6)；最後，本研究更討論了各擴散特徵所對應的大氣因子及污染物特性，如地表風場、東北風強度、大環境氣壓場、污染物日濃度、濃度標高百分比等等，嘗試建立天氣因子與擴散特徵之關聯性。

WRF and AI’S

作者年代地區應用方法
Jiang et al., (2018)29-typhopon forecastDL
Jensen et al., (2019)30(a tool)-CNN
Weyn et al., (2021)31全球DLWP, DLSEMCNN
Xu et al., 20213216 locationspara. testingdeep ML
Hatfield et al., (2021)33-climate predictionsNN for 4dVAR
Uchôa da Silva et al., (2022)34-convective predictionRF
Singh et al., (2023)35IndiaNWPDL,DLWP-CS
He et al., (2023)36-finegrid predictionDL
Liu et al., (2023)37--NN for 3dVAR
Zhong et al., (2023)38--WRF–ML v1.0
Sayeed et al., 202139南韓NWPWRF+CNN

Weyne and Durran

  • Durran, D., Weyn, J., Cresswell-Clay, N., Caruana, R. (2021). CAN DEEP LEARNING REPLACE CURRENT NUMERICAL WEATHER PREDICTION MODELS?aisis-2021.nucleares.unam.mx
  • DALE DURRAN, JONATHAN WEYN, NATHANIEL CRESSWELL-CLAY, RICH CARUANA(2022) DEEP LEARNING WEATHER PREDICTION: EPISTEMOLOGY AND NEW SCIENTIFIC HORIZONS, ECMWF 2022.
  • MMM Seminar: Replacing Current NWP with Deep Learning Weather Prediction and Extensions to a Full Earth-System Model , Mesoscale & Microscale Meteorology Laboratory, 2023/3

Spatio-Temporal Graph general surveys

Ren’s survey(2020)

Ren, X., Li, X., Ren, K., Song, J., Xu, Z., Deng, K., Wang, X. (2020). Deep Learning-Based Weather Prediction: A Survey. Big Data Research 23, 100178. doi40

  • In this paper, we survey the state-of-the-art studies of deep learning-based weather forecasting, in the aspects of the design of neural network (NN) architectures, spatial and temporal scales, as well as the datasets and benchmarks. Then we analyze the advantages and disadvantages of DLWP by comparing it with the conventional NWP, and summarize the potential future research topics of DLWP.

Pytorch Utilization41

S/T Satellite data applications

  • reviewing on Satellite image time series (SITS) ML works by Moskolaï et al., 202144

Wang et al. survey (2022)

Wang, S., Cao, J., Yu, P.S. (2022). Deep Learning for Spatio-Temporal Data Mining: A Survey. IEEE Transactions on Knowledge and Data Engineering 34, 3681–3700. doi 45

(Autoencoder (AE) and Stacked AE.)

Sahili and Awad(2023)

Sahili and Awad(2023)Spatio-Temporal Graph Neural Networks: A Survey46

Jin et al.(2023) survey for Predictive Learning in Urban Computing

  • Jin, G., Liang, Y., Fang, Y., Huang, J., Zhang, J., Zheng, Y. (2023)47. Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey.arXiv:2303.14483


  1. Li, J., Heap, A.D., Potter, A., Daniell, J.J. (2011). Application of machine learning methods to spatial interpolation of environmental variables. Environmental Modelling & Software 26, 1647–1659. doi ↩

  2. Zhang, Junbo, Yu Zheng, and Dekang Qi. “Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction.” AAAI. 2017. ↩

  3. Dixon, M.F., Polson, N.G., Sokolov, V.O. (2018). Deep Learning for Spatio-Temporal Modeling: Dynamic Traffic Flows and High Frequency Trading.(pdf) ↩

  4. Helber, P., Bischke, B., Dengel, A., Borth, D. (2019). EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 12, 2217–2226. doi ↩

  5. Le, V.-D., Bui, T.-C., Cha, S.K. (2019). Spatiotemporal deep learning model for citywide air pollution interpolation and prediction. arxiv.org ↩

  6. Abirami, S., Chitra, P. (2021). Regional air quality forecasting using spatiotemporal deep learning. Journal of Cleaner Production 283, 125341. doi ↩

  7. Shi C., Wang Y. (2021). Non-parametric machine learning methods for interpolation of spatially varying non-stationary and non-Gaussian geotechnical properties. dxqy 12, 339–350. doi ↩

  8. Leirvik, T., Yuan, M. (2021). A Machine Learning Technique for Spatial Interpolation of Solar Radiation Observations. Earth and Space Science 8, doi. ↩

  9. Wang, Y. (Victor), Sebastian, A., Kim, S.H., Piechota, T., Kafatos, M. (2021). Deep Learning for Spatial Interpolation of Rainfall Events (other). Authorea. December 06, 2021. doi,pdf ↩

  10. Melker Hoglund(2022) Machine Learning Methods for Spatial Interpolation of Wind, addvised by Anders Szepessy and Jonas Kiessling, KTH ROYAL INSTITUTE OF TECHNOLOGYSCHOOL OF ENGINEERING SCIENCES, 2020. ↩

  11. Tom Hengl, Leandro Parente, Carmelo Bonannella and contributors(2022)MLR, Spatial and spatiotemporal interpolation using Ensemble Machine Learning based on Garrett Grolemund and contributors2017 R for Data Science, Hadley Wickham. Also see zenodo ↩

  12. Kirkwood, C., Economou, T., Pugeault, N., Odbert, H. (2022). Bayesian Deep Learning for Spatial Interpolation in the Presence of Auxiliary Information. Math Geosci 54, 507–531. doi ↩

  13. Kim, J., Lee, Y., Lee, M.-H., Hong, S.-Y. (2022). A Comparative Study of Machine Learning and Spatial Interpolation Methods for Predicting House Prices. Sustainability 14, 9056. doi ↩

  14. Zhang, M., Yu, D., Li, Y., Zhao, L. (2022). Deep geometric neural network for spatial interpolation, in: Proceedings of the 30th International Conference on Advances in Geographic Information Systems, Association for Computing Machinery, New York, NY, USA, pp. 1–4. doi ↩

  15. Elbaz, K., Hoteit, I., Shaban, W.M., Shen, S.-L. (2023). Spatiotemporal air quality forecasting and health risk assessment over smart city of NEOM. Chemosphere 313, 137636. doi ↩

  16. Oliveira Santos, V., Costa Rocha, P.A., Scott, J., Van Griensven Thé, J., Gharabaghi, B. (2023). Spatiotemporal Air Pollution Forecasting in Houston-TX: A Case Study for Ozone Using Deep Graph Neural Networks. Atmosphere 14, 308. doi ↩

  17. Friberg, M.D., Zhai, X., Holmes, H.A., Chang, H.H., Strickland, M.J., Sarnat, S.E., Tolbert, P.E., Russell, A.G., Mulholland, J.A. (2016). Method for Fusing Observational Data and Chemical Transport Model Simulations To Estimate Spatiotemporally Resolved Ambient Air Pollution. Environ. Sci. Technol. 50, 3695–3705. doi ↩

  18. Lyu, B., Hu, Y., Zhang, W., Du, Y., Luo, B., Sun, X., Sun, Z., Deng, Z., Wang, Xiaojiang, Liu, J., Wang, Xuesong, Russell, A.G. (2019). Fusion Method Combining Ground-Level Observations with Chemical Transport Model Predictions Using an Ensemble Deep Learning Framework: Application in China to Estimate Spatiotemporally-Resolved PM2.5 Exposure Fields in 2014–2017. Environ. Sci. Technol. 53, 7306–7315. doi ↩

  19. Eslami, E. 1985- (2020). Applications of Deep Learning in Atmospheric Sciences: Air Quality Forecasting, Post-Processing, and Hurricane Tracking (Thesis). ↩

  20. O’Neill, S.M., Diao, M., Raffuse, S., Al-Hamdan, M., Barik, M., Jia, Y., Reid, S., Zou, Y., Tong, D., West, J.J., Wilkins, J., Marsha, A., Freedman, F., Vargo, J., Larkin, N.K., Alvarado, E., Loesche, P. (2021). A multi-analysis approach for estimating regional health impacts from the 2017 Northern California wildfires. Journal of the Air & Waste Management Association 71, 791–814. doi ↩

  21. Sayeed, A., Lops, Y., Choi, Y., Jung, J., Khan, A. (2021). Bias Correcting and Extending the PM Forecast by CMAQ up to 7 days using Deep Convolutional Neural Networks. Atmospheric Environment. doi ↩

  22. Sun, H., Fung, J.C.H., Chen, Y., Chen, W., Li, Z., Huang, Y., Lin, C., Hu, M., Lu, X. (2021). Improvement of PM2.5 and O3 forecasting by integration of 3D numerical simulation with deep learning techniques. Sustainable Cities and Society 75, 103372. doi ↩

  23. Dharmalingam, S., Senthilkumar, N., D’Souza, R.R., Hu, Y., Chang, H.H., Ebelt, S., Yu, H., Kim, C.S., Rohr, A. (2022). Developing air pollution concentration fields for health studies using multiple methods: Cross-comparison and evaluation. Environmental Research 207, 112207. doi ↩

  24. Ren, X., Mi, Z., Cai, T., Nolte, C.G., Georgopoulos, P.G. (2022). Flexible Bayesian Ensemble Machine Learning Framework for Predicting Local Ozone Concentrations. Environ. Sci. Technol. 56, 3871–3883. doi ↩

  25. Hong, H., Choi, I., Jeon, H., Kim, Y., Lee, J.-B., Park, C.H., Kim, H.S. (2022). An Air Pollutants Prediction Method Integrating Numerical Models and Artificial Intelligence Models Targeting the Area around Busan Port in Korea. Atmosphere 13, 1462. doi ↩

  26. Huang, R., Li, Z., Ivey, C.E., Zhai, X., Shi, G., Mulholland, J.A., Devlin, R., Russell, A.G. (2022). Application of an improved gas-constrained source apportionment method using data fused fields: A case study in North Carolina, USA. Atmospheric Environment 276, 119031. doi ↩

  27. Jang, E., Kim, M., Do, W., Park, G., Yoo, E. (2022). Real-time estimation of PM2.5 concentrations at high spatial resolution in Busan by fusing observational data with chemical transport model outputs. Atmospheric Pollution Research 13, 101277. doi ↩

  28. Huang, C., Niu, T., Wu, H., Qu, Y., Wang, T., Li, M., Li, R., Liu, H. (2023). A Data Assimilation Method Combined with Machine Learning and Its Application to Anthropogenic Emission Adjustment in CMAQ. Remote Sensing 15, 1711. doi ↩

  29. Jiang, G.-Q., Xu, J., Wei, J. (2018). A Deep Learning Algorithm of Neural Network for the Parameterization of Typhoon-Ocean Feedback in Typhoon Forecast Models. Geophysical Research Letters 45, 3706–3716. doi ↩

  30. Jensen, D., Lucas, D., Anderson-Bergman, C., Wharton, S. (2019). iWet: The Intelligent WRF Ensemble Tool. see NOAA poster ↩

  31. Weyn, J.A., Durran, D.R., Caruana, R., Cresswell-Clay, N. (2021). Sub-Seasonal Forecasting With a Large Ensemble of Deep-Learning Weather Prediction Models. Journal of Advances in Modeling Earth Systems 13, e2021MS002502. doi ↩

  32. Xu, F., Shi, W., Du, Y., Chen, Z., Lu, Y. (2021). DeepPE: Emulating Parameterization in Numerical Weather Forecast Model Through Bidirectional Network, in: Dong, Y., Kourtellis, N., Hammer, B., Lozano, J.A. (Eds.), Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track, Springer International Publishing, Cham, pp. 87–101. doi ↩

  33. Hatfield, S., Chantry, M., Dueben, P., Lopez, P., Geer, A., Palmer, T. (2021). Building Tangent-Linear and Adjoint Models for Data Assimilation With Neural Networks. Journal of Advances in Modeling Earth Systems 13, e2021MS002521. doi ↩

  34. Uchôa da Silva, Y., França, G.B., Ruivo, H.M., Fraga de Campos Velho, H. (2022). Forecast of convective events via hybrid model: WRF and machine learning algorithms. Applied Computing and Geosciences 16, 100099. doi ↩

  35. Singh, M., Acharya, N., Patel, P., Jamshidi, S., Yang, Z.-L., Kumar, B., Rao, S., Gill, S.S., Chattopadhyay, R., Nanjundiah, R.S., Niyogi, D. (2023). A modified deep learning weather prediction using cubed sphere for global precipitation. Frontiers in Climate 4. ↩

  36. He, J., Liu, X., Wang, H., Zhu, D., Liu, Z. (2023). A high-precision prediction method for coarse grids based on deep learning and the Weather Research and Forecasting model (preprint). In Review. doi ↩

  37. Liu, Y., Liu, J., Li, C., Liu, L., Wang, Y. (2023). A WRF/WRF-Hydro Coupled Forecasting System with Real-Time Precipitation–Runoff Updating Based on 3Dvar Data Assimilation and Deep Learning. Water 15, 1716. doi ↩

  38. Zhong, X., Ma, Z., Yao, Y., Xu, L., Wu, Y., Wang, Z. (2023). WRF–ML v1.0: a bridge between WRF v4.3 and machine learning parameterizations and its application to atmospheric radiative transfer. Geoscientific Model Development 16, 199–209. doi ↩

  39. Sayeed, A., Choi, Y., Jung, J., Lops, Y., Eslami, E., Salman, A.K. (2021). A Deep Convolutional Neural Network Model for Improving WRF Simulations. IEEE Transactions on Neural Networks and Learning Systems 34, 750–760. pdf ↩

  40. Ren, X., Li, X., Ren, K., Song, J., Xu, Z., Deng, K., Wang, X. (2020). Deep Learning-Based Weather Prediction: A Survey. Big Data Research 23, 100178. doi ↩

  41. Rozemberczki, B., Scherer, P., He, Y., Panagopoulos, G., Riedel, A., Astefanoaei, M., Kiss, O., Beres, F., López, G., Collignon, N., Sarkar, R. (2021). PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models. arXiv:2104.07788 ↩

  42. Li, Y., Yu, R., Shahabi, C., Liu, Y. (2018). Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting. doi ↩

  43. Taheri, A., Berger-Wolf, T. (2020). Predictive temporal embedding of dynamic graphs, in: Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, Association for Computing Machinery, New York, NY, USA, pp. 57–64. doi ↩

  44. Moskolaï, W.R., Abdou, W., Dipanda, A., Kolyang (2021). Application of Deep Learning Architectures for Satellite Image Time Series Prediction: A Review. Remote Sensing 13, 4822. doi ↩

  45. Wang, S., Cao, J., Yu, P.S. (2022). Deep Learning for Spatio-Temporal Data Mining: A Survey. IEEE Transactions on Knowledge and Data Engineering 34, 3681–3700. doi ↩

  46. Zahraa Al Sahili, Mariette Awad (2023). Spatio-Temporal Graph Neural Networks: A Survey. arxiv 2301/2301.10569. ↩

  47. Jin, G., Liang, Y., Fang, Y., Huang, J., Zhang, J., Zheng, Y. (2023). Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey.arXiv:2303.14483 ↩