Please find below the
Finalist Evaluation
Semi-Finalist Evaluation
Judges'' ratings
• | Novelty: | |
• | Feasibility: | |
• | Impact: | |
• | Presentation: |
Judges'' comments
Comments:
An interesting approach towards rain enhancement. Such a project would require an interdisciplinary which usually results in innovative solutions. I completely support such proposals.
I think there is a clear lack of understanding of the process. A simple non-linear prediction system is not enough here. It is a complex process and a significant understanding of the underlying physics is required even for modeling. Even if you were to do a numerical modeling with a non-linear predicting system like Bayesian Networks, what would be the input data for your models?
Mona Al Zubaidi Jul 24, 2017 09:21
Member
| Proposal creator One of the bayesian networks key advantages is the ability to integrate domain experts/knowledge judgments in the process, and hence building an interactive model. There are several different approaches to achieve that, and this should always be taken into consideration when doing the research. It's a very important question to ask: where and how to get the data? There are several resources that provide data, there's a data that available in R which covers 24 observations from the cloud seeding experiments in Florida: https://vincentarelbundock.github.io/Rdatasets/doc/HSAUR/clouds.html There's another huge synthesised rainfall dataset that was collected between 1960-2005 in Australia, however it's not publicly available(we have to request for that): https://figshare.com/articles/Seeding_the_Commons_-_Monash_University_Research_Data_Collections_Project/4993892 https://researchdata.ands.org.au/cloud-seeding/9320 Cloud seeding in the UAE started in 1990, I couldn't find any dataset online about the results of these experiments, but I believe there is some data collected and documented during these years for research purposes, and we have to ask them to give us the data (i'm still not sure about this). |