We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Delimitation of low topsoil moisture content areas in a vineyard using remote sensing imagery (Sentinel-1 and Sentinel-2) in a Mediterranean-climate region.
- Authors
MENDES, MARIA PAULA; MATIAS, MAGDA; CARRILHO GOMES, RUI; PAULA FALCÃO, ANA
- Abstract
Irrigation can be responsible for salt accumulation in the root zone of grapevines when late autumn and winter precipitation is not enough to leach salts from the soil upper horizons, turning the soil unsuitable for grape production. The aim of this work is to present a novel methodology to outline areas, within a drip-irrigated vineyard, with a low soil moisture content (SMC) during, and after, an 11-month agricultural drought. Soil moisture (SM) field measurements were performed in two plots at the vineyard, followed by a geostatistical method (indicator kriging) to estimate the SM class probabilities according to a threshold value, enlarging the training set for the classification algorithms. The logistic regression (LR) and Random Forest (RF) methods used the features of the Sentinel-1 and Sentinel-2 images and terrain parameters to classify the SMC probabilities at the vineyard. Both methods classified the highest SMC probabilities above 14% that is located close to the stream at the lower altitudes. The RF method performed very well in classifying the topsoil zones with a lower SMC during the autumn-winter period. This delineation allows the prevention of the occurrence of areas affected by salinisation, indicating which areas will need irrigation management strategies to control the salinity, especially under climate change, and the expected increase in droughts.
- Subjects
SENTINEL-1 (Artificial satellite); SOIL salinity; REMOTE sensing; SOIL moisture; TOPSOIL; VINEYARDS; RANDOM forest algorithms; IRRIGATION management
- Publication
Soil & Water Research, 2021, Vol 16, Issue 2, p85
- ISSN
1801-5395
- Publication type
Article
- DOI
10.17221/101/2019-SWR