AUTHOR=Aka Kadio S. R. , Akpavi Semihinva , Dibi N’Da Hyppolite , Kabo-Bah Amos T. , Gyilbag Amatus , Boamah Edward 

TITLE=Toward understanding land use land cover changes and their effects on land surface temperature in yam production area, Côte d'Ivoire, Gontougo Region, using remote sensing and machine learning tools (Google Earth Engine)

JOURNAL=Frontiers in Remote Sensing

VOLUME=Volume 4 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/remote-sensing/articles/10.3389/frsen.2023.1221757

DOI=10.3389/frsen.2023.1221757

ISSN=2673-6187

ABSTRACT=Land use and land cover (LULC) changes are one of the main factors contributing to ecosystem degradation and global climate change. This study used Gontougo region as a study area which is a fast-changing in land occupation and most vulnerable to climate change. Machine learning method through Google Earth Engine (GEE) is a widely used technique for the spatio-temporal evaluation of LULC changes and their effects on Land Surface Temperature (LST). Using Landsat 8 OLI and TIRS images from 2015 to 2022, we analysed vegetation cover through the Normalized Difference Vegetation Index (NDVI) and we computed LST. The correlation between those was significant and the Pearson correlation (r) was negative for each correlation over the year. The NDVI and LST reclassifications correspondence have also shown that Non-vegetation land corresponds to very high temperature (34.33 to 45.22°C in 2015 and 34.26 to 45.81°C in 2022), and High vegetation land corresponds to low temperature (17.33 to 28.77°C in 2015 and 16.53 29.11°C in 2022). Moreover, using Random Forest Algorithm and Sentinel-2 images for 2015 and 2022, we obtained six LULC classes: Bareland and Settlement, Forest, Waterbody, Savannah, Annual crops and Perennial crops. The overall accuracy for each LULC map was respectively 93.77% and 96.01%. Similarly, the kappa was 0.87 in 2015 and. 0.92 in 2022. The LULC classes forest and annual crops lost respectively 48.13% and 65.14% of their areas for the benefit of perennial crops from 2015 to 2022. The correlation between LULC and LST showed that the forest class registered the low mean temperature (28.69°C in 2015 and 28.46°C in 2022) and the bareland/settlement the highest mean temperature (35.18°C in 2015 and 35.41°C in 2022). The results show that high-resolution images can be used for monitoring biophysical parameters in vegetation and surface temperature and has benefits for evaluating food security.