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
Upgrade or Replace There are two approaches when upgrading an existing system: improve the current system or replace the system. The former enjoys the extensive amount of previous work, but it also faces possible short-comings inherit to a design based on outdated technologies. The latter option provides an opportunity to design a solution based on the latest technologies, it but may prove costly to replace old system. Most of the researchers deemed replacement too expensive and opted to supplement the existing system by solving the existing problems. Professor Tapio Schneider and his colleagues decided otherwise (Perkins, 2018). They created a team called CliMA (Perkins, 2018). Picture 1. Professor Tapio Schneider. From New Climate Model to Be Built from the Ground Up by S. Diani, 2019, https://www.sciencemag.org/sites/default/files/styles/inline__699w__no_aspect/public/350cs_80727X_Tapio_0.jpg?itok=6HRPTU8g New Climate Model This young but ambitious project aims to replace ...
AI for Earth In the Microsoft blog called “Researchers turn to AI in a bid to improve weather forecasts” by Roach, the author highlights some of the company's contribution to the research that benefits mankind. Through the AI for Earth initiative, the company funds various challenging research projects that studies Earth. The blog also highlights the social activities, such as hackathons, that illustrates some of the current trends of using machine learning to solve difficult problems. References Roach, J. (2019, May 20). Researchers turn to AI in a bid to improve weather forecasts. Retrieved May 26, 2019, from https://blogs.microsoft.com/ai/ai-subseasonal-weather-forecast/
Origin The “AI and climate: On the bleeding edge with a pioneering researcher” by journalist Crowder is a dialogue between the journalist and professor Monteleoni. The professor is credited to coining the term, ‘climate informatics’ in 2012 (Crowder, 2018). Crowder interviewed the professor after 6 years to find out more about the new-born field of research and just how much the field has grown since. Picture 1. Professor Monteleoni. From Predictability assessment of northeast monsoon rainfall in India using sea surface temperature anomaly through statistical and machine learning techniques by L. Crowder, 2018. https://thebulletin.org/wp-content/uploads/2018/02/cmontel-680x1024.jpg In the conversation, the professor described climate informatics as “innovation at the intersection of data science and climate science” (Crowder 2018). This is similar to bioinformatics that became popularized more than a decade ago which combined biological data with data science, and professor...
Comments
Post a Comment