Short-Term Rainfall Prediction Based on Radar Echo Using an Improved Self-Attention PredRNN Deep Learning Model

Round 1

Reviewer 1 Report

 

This study proposes a precipitation forecasting model based on the PredRNN Deep Learning Model to improve the performance of the model.  I always welcome studies with the aim of improving the Spatio-temporal characterization of precipitation estimates.  In my view, it does not make a new contribution in terms of precipitation forecast. I have some recommendations for future submission.

 

• The authors mostly focused on PredRNN Deep Learning Model instead of significant science/engineering applications. In your introduction section, you mainly explained your proposed method. First, you should discuss the significant uncertainties in satellite datasets throughout warm and cold seasons, over the study regions. Then you should introduce other Machine learning-based rainfall forecasting models where they utilize satellite precipitation products along with auxiliary variables such as soil moisture, temperature elevation, etc. But you mentioned very limited study. You just mention one study which is the PredRNN Deep Learning based forecasting model. There are tons of ML-based forecasting models such as Quantile regression forest, SVM,RF, boosted tree, etc., which you need to introduce. I think the authors need to propose a detailed comprehensive introduction section. What is the uniqueness of the proposed technique and its potential impacts, over other established techniques? The authors should explain with a couple of new paragraphs on this aspect in the introduction section. Also, you need to provide more literature review in the introduction section associated with the research gap/limitation

 

 

·         At the global scale, precipitation estimation primarily relies on satellite-based observations. Why you did not consider any of them. A better explanation of why the authors did not consider satellite precipitation products such as  TRMM 3B43v7, PERSIANN-CDR, and IMERG were required? For instance, why you did not include Global Satellite Mapping of Precipitation (GSMaP), and Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks (PERSIANN)? Recent studies showed that extensive evaluation of all these global-scale high-resolution satellite-based rainfall (SBR) products were evaluated and explained the merit of those precipitation products in accurate precipitation estimates. The authors should explain this aspect in the introduction section. Please include GSMaP and CMORPH in your analysis.

• Can you provide a study area map where you can indicate your selected catchments? As the model was applied for different climatic conditions, can you provide climatic information for the selected study areas? You can show Köppen–Geiger climatic zones on the map.

• I suggest the use of the modified Kling-Gupta efficiency. This index decomposes the total performance of the precipitation products into linear correlation (r), bias (beta), and variability ratio (gamma). Also, the performances obtained from this index can be compared among precipitation products.

• Did you take into consideration the reporting time difference between your features and observation rain? Please explain.
• Discussion: The discussion must be expanded, and more references added. In the introduction, you mention articles that can be used to discuss and compare your results.

 

Here are the few ML-based rain forecast model based on quantile regression forests (QRF), Random forest( RF), SVM, neural net  :

 

Bhuiyan, et al. "A nonparametric statistical technique for modeling overland TMI (2A12) rainfall retrieval error." IEEE Geoscience and Remote Sensing Letters 14.11 (2017): 1898-1902.

Zhang, Ling, et al. "Merging multiple satellite-based precipitation products and gauge observations using a novel double machine learning approach." Journal of Hydrology 594 (2021): 125969.

Chiang, et al. "Precipitation assimilation from gauge and satellite products by a Bayesian method with Gamma distribution." International Journal of Remote Sensing 42.3 (2021): 1017-1034.

 Banadkooki, et al. "Precipitation forecasting using multilayer neural network and support vector machine optimization based on flow regime algorithm taking into account uncertainties of soft computing models." Sustainability 11.23 (2019): 6681.

Banadkooki, et al. "Precipitation forecasting using multilayer neural network and support vector machine optimization based on flow regime algorithm taking into account uncertainties of soft computing models." Sustainability 11.23 (2019): 6681.

Kolluru, et al. "Secondary precipitation estimate merging using machine learning: development and evaluation over Krishna river basin, India." Remote Sensing 12.18 (2020): 3013.

 

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Dear Authors,

Your paper deals with interesting and useful topic i.e. short-range precipitation amount forecast using weather radar echo images by neural networks. However, because of atmosphere is a dynamical system such a context is important to keep all the time. This is a reaso, if you planning to publish your paper in the "Atmosphere", please consider possibility to combine neura network results with conventional approaches described in your reference [1-3].

Beside other, weather radar images represent content of water in the air, but precipitation is water on the ground. Radar images interpretation into rainfall depends on position of weather radars, topography of terrain, precipitation type (convective or stratiform) etc.

Some other comments are in enclosed pdf.

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Please see attached. This paper does a great job describing the complex ML model applied here, but the validation needs some work.

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

The authors significantly improved the quality of the paper by addressing most of the previous comments. This research work will be very effective for the Water resources community. I recommend the manuscript for publication !!

Author Response

Thanks for your comments, which is highly appreciated. Thanks for your approval of our work. Your comments are very helpful to improve the quality of our manuscripts. I have gained a lot from revising the manuscript according to your comments. Your comments have also pointed the way for our future research. Thank you again sincerely!

Reviewer 2 Report

Dear authors,

I can see some improvements of previous version of the manuscript. In addition to necessary  improvement  of notation in Equation (1), vector and matrix notation, Appendix A of the present cover letter)  there is a space for improvement in involvment of physical background of the process.  Could be these neural network technique „power interpreted“ in terms of stochastic relationship between measured statistical variables (e.g. radar echo) as a consequence of physical conditions different spatio-temporal scales and environmental conditions as orographical  conditions, part of day or season, type of weather (cyclonic, anticyclone, cold or warm atmospheric front, air mass convection etc.).  Does neural networks are based on famous „similarity“ theory in meteorology: „similar initial condition is following with similar development“. Partly it is true but limited because of „non-linearities“  in atmospheric processes spatio-temporal developments. For example,  climatological conceptual paths of radar echo images,  like cyclonic van Beber’s parts in Europe, could be useful tool towards physical interpretation of neural networks’ predition power.

I can recommend publication of this version of the manuscript after minor revision.

 

 

 

 

 

 

 

 

 

 

 

Appendix A:

Link to Wikipedia: https://en.wikipedia.org/wiki/Mahalanobis_distance „

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

The paper is much improved. Thank you. My only remaining concern is again regarding the geography of the study region: where in China is the Ninxia Hui Autonomous region?

Author Response

Please see the attachment.

Author Response File: Author Response.pdf