Summary of Comparing Skill Of Historical Rainfall Data Based Monsoon Rainfall Prediction in India with Ncep-nwp Forecasts, by Apoorva Narula et al.
Comparing skill of historical rainfall data based monsoon rainfall prediction in India with NCEP-NWP forecasts
by Apoorva Narula, Aastha Jain, Jatin Batra, Sandeep Juneja
First submitted to arxiv on: 12 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper explores the problem of forecasting rainfall in India during the four monsoon months, with a focus on one-day and three-day predictions. The authors train neural networks using historical daily gridded precipitation data from 1901-2022, at a spatial resolution of 1° x 1°. They compare these results to numerical weather prediction (NWP) forecasts from NCEP (National Centre for Environmental Prediction) available for the period 2011-2022. The authors find that deep learning-based predictions are more accurate than NWP and persistence-based methods, with average errors reduced by up to 68% for three-day predictions. They also show that incorporating data up to 20 days in the past can improve forecast accuracy using transformer-based architectures. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about predicting rainfall in India during the monsoon season. The scientists trained computers to learn patterns from old weather data and then tested how well they could predict future rain. They compared their results to forecasts made by special weather machines, and found that their computer predictions were better. This is important because it can help people prepare for heavy rain or droughts, which affect many people in India. |
Keywords
* Artificial intelligence * Deep learning * Transformer
