Sentinel Data and Machine Learning Algorithms for Soil Moisture Land Classification

• Published in: Biology and life sciences forum 2023-11, Vol.27 (1), p.55
• Main Authors: Salah Benmahmoud, Olfa Charfi, Chiraz Masmoudi Charfi
• Format: Article
• Language: English
• Subjects: land crops; machine learning algorithms; rainfall; sentinel data; soil moisture
• ISSN: 2673-9976
• DOI: 10.3390/IECAG2023-15972

Tunisia needs judicious water allocation to mitigate drought. Remote sensing tools, such as Sentinel-1 and Sentinel-2, can be used to estimate soil water status and monitor changes in soil moisture and vegetation cover. The study area covers the Kairouan governorate in the center of Tunisia, (35°40′33.29″ N, 10°5′30.26″ E), which is characterized by a flat relief (plain) covering an area of 6800 Km2 and belonging to the ‘upper arid bioclimatic stage’. The study proposes a formula called “ER” to estimate soil water status from Sentinel-1 data, two color composition images to control changes in soil moisture and vegetation cover, and unsupervised ISODATA and k-means classifications to monitor the impact of climate change and land use. The data used are nine Sentinel-1 images and twelve Sentinel-2 images downloaded from the Copernicus platform at the dates given. The VV and VH Sentinel-1 GRD Level1 products were selected at different dates based on the daily precipitation amount (PA) of the studied region: PA > 55 mm,18.5 mm < PA < 33.5 mm, PA < 10 mm and PA = 0 mm for Sentinel-2, with results collected on 29/01, 23/2, 25/03, 24/04, 16/05, 11/05, 05/06, 13/06, 23/07, 24/08, 18/09 and 11/10 in 2019. For Sentinel-1, the dates of acquisition of images were 24/01, 23/02, 25/03, 12/04, 24/05, 12/06, 27/07, 15/09 and 09/10 in 2019. We chose cloudless images and we chose close dates for the two sentinels, which correspond to the dates of our field visit carried out in June and October 2019. Validation was carried out using two main criteria: (i) the measured mean precipitation deviation over successive months (EP) and (ii) the three reference land cover types (LC): cereals (LC1), fallow land (LC2) and bare soil (LC3). For this case study, three cases of EP were considered: (1) no precipitation (EP ≤ 0), (2) low precipitation (0 < EP ≤ 20 mm), and (3) high precipitation (EP > 20 mm). The results showed that, considering the VH polarization, we obtain ER < 0 for LC3 and ER ≈ 0 for the LC1 and LC2 terrestrial cultures when EP ≤ 0; ER > 0 for LC3 and ER ≈ 0 for the LC1 and LC2 terrestrial cultures when (0 < EP ≤ 20 mm); and ER > 0 for all LCs and the value increases with high rainfall. We validated these ER results using image composition and classified images.