QLand|| QArdh is a project worked on for the NYU Quantum Computing Hackathon, aiming to solve social good in the Arab world and/or global issues.
QLand|| QArdh project is aiming to use quantum computing to help in desertification monitoring and predicting future pattern desertification. Desertification is the process when fertile lands become deserts! Two-thirds of the earth is undergoing desertification. As it is caused by many factors like human acts( examples) and climate change it is challenging to analyze all the possible contributing factors.
Monitoring and predicting desertification in classical methods rely on choosing the right combination of factors that would result in the correct prediction.
Project Outline
1- Data sets were collected and generated based on Iraq desertification analysis https://www.omdena.com/blog/desertification-detection-with-machine-learning-and-satellite-data 2- Using classical machine learning models: RF, SVM with two different factors of the four( NVDI, LST) 3- Solving Quantum job schedule problems using QAOA( Quantum Approximation Optimization Algorithm)
In studying anthropologic desertification, our team has found that many of the research papers conduct thorough analysis on 4 main criteria: Normal Difference Vegetation Index (NVDI), Land Surface Temperature (LST), DGSI, Albedo. However, many researchers cite [: Feng, K.; Wang, T.; Liu, S.;Kang, W.; Chen, X.; Guo, Z.; Zhi, Y.Monitoring Desertification UsingMachine-Learning Techniques with Multiple Indicators Derived from MODIS Images in Mu Us SandyLand, China. Remote Sens. 2022, 14,2663. https://doi.org/10.3390/rs14112663] that several challenges exist in forecasting and prediction.
At QArdh, we focus on solving a pain point of such researchers, which involves studying the above metrics on various models and obtaining results efficiently. Quantum Job scheduling problem Quantum job scheduling problem is...