Monsoon Season in India

Figure 1. The study zone: the India Peninsula. From Predictability assessment of northeast monsoon rainfall in India using sea surface temperature anomaly through statistical and machine learning techniques, by Y. Dash, 2019.

Purpose

Professor Dash and his colleagues investigated correlation between northeast monsoon rainfall (NEMR) and sea surface temperature (SST) in hopes of finding an effective way to predict flood and draughts in the Indian peninsular (Dash, et al. 2019). In their approach, they compared three different methods of machine learning: linear regression, artificial neural network, and extreme learning machine (Dash, et al. 2019).

Focus

This research was had multiple focuses. As with many other researches currently studying the feasibility of using machine learning in the study of climate change, the research aimed to compare the efficiency and scalability of various machine learning algorithms to study weather patterns. Not only that, it also was poised to solve a real-world challenge: it was the first attempt made at linking the two data sets to create meaningful information (Dash, et al. 2019).

Conclusion

The researchers concluded that of the three methods used, ELM produced the most promising results, and that SST indeed has a potential in predicting NEMR and help prepare people for potential flooding or draught (Dash, et al. 2019).

References

  • Dash, Y, Mishra, SK, Panigrahi, BK. Predictability assessment of northeast monsoon rainfall in India using sea surface temperature anomaly through statistical and machine learning techniques. Environmetrics. 2019; 30:e2533. https://doi.org/10.1002/env.2533

Comments

Popular posts from this blog

AI for Earth

Faceapp for Houses

Early Look at Machine Learning