top of page
Search
Writer's pictureCecilia Wandiga

☘️🔬Understanding Ecochemistry🔬☘️

👩‍🔬𝐀𝐬𝐤 𝐚 𝐒𝐜𝐢𝐞𝐧𝐭𝐢𝐬𝐭: Prof. Shem Wandiga, our Managing Trustee, about his 50 years of atmospheric research in Africa.




He has now added a machine learning publication to his distinguished list of over 140 papers, 134 conference presentations, 26 books and chapters in books, 11 public lectures at international conferences, 10 government reports and 13 consultancy reports.    




📢 Presented at: The 15th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2023, Bangkok Thailand , 22-23 Dec. 2023


👩‍💻AbstractThis paper presents a comprehensive evaluation of machine learning algorithms for rainfall prediction in the Nyando region. The study employs LSTM, XGBoost, Random Forest, and SVR algorithms, exploring both univariate and multivariate models to enhance the accuracy of predictions. Additionally, the paper examines three different outlier filtering methods and assesses their impact on the final prediction outcomes. The research endeavours to contribute valuable insights to the field of rainfall prediction and disaster management. By providing accurate and reliable rainfall predictions, this study aims to aid communities in the Nyando region and similar areas in their efforts to effectively mitigate the adverse impacts of extreme weather events.


💡 Meaning — Imagine we have a magical treasure map to predict when it might rain in a special place called Nyando. We use smart machines to learn how the weather works and make better predictions. It's like having superhero friends (LSTM, XGBoost, Random Forest, and SVR) who help us understand the weather puzzle. By doing this, we hope to help the people in Nyando be ready for rain and stay safe from tricky weather surprises.





📘 Index Terms—Rainfall prediction, Machine learning, LSTM, SVR, Random Forest, XGBoost, Disaster preparedness


If you are not a member of Research gate, you can download it from our CSTI website 


🛤 𝐍𝐞𝐱𝐭 𝐒𝐭𝐞𝐩

Machine learning algorithms for GHG emissions

"Prof Wandiga pointed out industrialization activities as one of the GHGs contributors making the atmosphere warmer by at least than one degree."

"The Expert said Intergovernmental Panel on Climate Change (IPCC) report 2014, indicates that Carbon Dioxide is the largest occupant of the atmosphere at 65%, Methane gas 16%, Nitrous Oxide 6% and Fluorinated gases such as Neon at 2%."


💡 Meaning—Imagine a wise person named Prof Wandiga telling us that when factories and big machines make things, they also make something called Greenhouse Gases. These gases make the air around us a bit warmer, like wearing a cozy blanket. The biggest one is like a superhero named Carbon Dioxide, followed by others like Methane, Nitrous Oxide, and Fluorinated gases, each with their special powers in the air!


He can now work with others to use tools inside ChatGPT to predict when it will rain. This is necessary because the superheroes named Carbon Dioxide, followed by others like Methane, Nitrous Oxide, and Fluorinated gases have been moving the rainclouds and hiding them!


👩‍🔬𝐂𝐢𝐭𝐢𝐳𝐞𝐧 𝐒𝐜𝐢𝐞𝐧𝐜𝐞

Did you know trees absorb methane and methane makes them catch fire faster?




📷 𝐂𝐨𝐥𝐥𝐚𝐠𝐞 𝐏𝐡𝐨𝐭𝐨 𝐂𝐫𝐞𝐝𝐢𝐭𝐬


Couple Walking in City NightCafe Studio (CSTI creation)

City of Nairobi Unsplash (Joecalih)

Trees Unsplash (Paul Arky)

192 views0 comments

Comments


bottom of page