Modeling the evolution of the maximum and minimum concentration point of CO2 on Madagascar

Harimino Andriamalala RAJAONARISOA

¹ Dynamic Atmosphere, Climate, and Ocean Laboratory, Physics and Applications, Sciences and Technologies, 

University of Antananarivo, Madagascar

² Mathematics, Computer Science and Applications, Faculty of Sciences and Technologies,

University of Toamasina, Madagascar

*Corresponding Author: [email protected]

The aim of this work is to locate and model the evolution of the point of maximum and minimum concentration of CO2 on Madagascar. The experiment is carried out using 85 pairs of low and high resolution CO2 concentration map images on Madagascar. The first step consists of super-resolving these images using the SRGAN algorithm to have more precision. The second step of the work is the location of the point of maximum and minimum concentration of CO2 using the image thresholding technique. After this step, we obtained the coordinates of the monthly evolution of these points. The third and final step relates to the modeling of the evolution of the latitude and longitude of said points by the ANFIS model. The results showed that the minimum (respectively maximum) concentration points are focused in the North, Central and South-Eastern part (respectively extreme North and Middle West part) of Madagascar.

ANFIS, Batch size, CO2, SRGAN, Image thresholding

Harimino Andriamalala RAJAONARISOA, Solofo RAFANOMEZANTSOA, Andriamasinoro RAHAJANIAINA, Adolphe Andriamanga RATIARISON (2024). Modeling the evolution of the maximum and minimum concentration point of CO2 on Madagascar. Journal of Artificial Intelligence and Systems, 6, 201–217. https://doi.org/10.33969/AIS.2024060114.

[1] Hervé, N. (2021). Synthèse du rapport AR6 du GIEC

[2] Pachauri, R. K., & Reisinger, A. (Eds.). (2008). Bilan 2007 des changements climatiques: Rapport de synthèse. GIEC.

[3] Borgen, S. K., Grønlund, A., Andrén, O., Kätterer, T., Tveito, O. E., Bakken, L. R., & Paustian, K. (2012). CO2 emissions from cropland in Norway estimated by IPCC default and Tier 2 methods. Greenhouse Gas Measurement and Management, 2(1), 5-21.

[4] Farret, R., & Gombert, P. (2018). Les principales techniques de captage du CO2: opportunités et difficultés. Géologues, 196, 76-8.

[5] Lecomte, F., Broutin, P., & Lebas, E. (2009). Le captage du CO2: Des technologies pour réduire les émissions de gaz à effet de serre. Editions Technip.

[6] Ledig, C. et al. (2017). Photo-realistic single image super-resolution using a generative adversarial network. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4681-4690).

[7] Bradley, D., & Roth, G. (2007). Adaptive thresholding using the integral image. Journal of graphics tools, 12(2), 13-21.

[8] Jang, J. S. (1993). ANFIS: adaptive-network-based fuzzy inference system. IEEE transactions on systems, man, and cybernetics, 23(3), 665-685.

[9] Rajaonarisoa, H. A. et al.(2023). Super Resolution Generative Adversarial Network Model parameter optimization to improve the quality of geostationary meteorological satellite images. Journal of Artificial Intelligence and Systems, 5(1), 115-124.

[10] Ostu, N. (1979). A threshold selection method from gray-level histograms. IEEE Trans SMC, 9, 62.

[11] Song, Q., & Chissom, B. S. (1993). Fuzzy time series and its models. Fuzzy sets and systems, 54(3), 269-277.

[12] Kiranyaz, S. et al. (2021). 1D Convolutional Neural Networks and applications: A survey. Mechanical systems and signal processing, 151, 107398.