Modelling the topsoil carbon stock of agricultural lands with the Stochastic Gradient Treeboost in a semi-arid Mediterranean region
详细信息 查看全文
- 作者：Calogero Schillacia ; b ; Luigi Lombardoc ; b ; Sergio Saiad ; sergio.saia@crea.gov.it" class="auth_mail" title="E-mail the corresponding author ; Maria Fantappiè ; e ; Michael Mä ; rkerb ; f ; Marco Acutisa
- 关键词：Soil organic carbon ; Stochastic modelling ; Terrain analysis ; Remote sensing ; Climate data
- 刊名：Geoderma
- 出版年：2017
- 出版时间：15 January 2017
- 年：2017
- 卷：286
- 期：Complete
- 页码：35-45
- 全文大小：2580 K
文摘
- •
Soil organic carbon (SOC) stock was estimated in a Mediterranean area using digital soil mapping techniques.
- •
Climate, texture and land use were found to be important predictors.
- •
The model used greatly improved SOC stock estimation compared to previous estimates.
- •
The panchromatic band of Landsat ETM + 7 was more predictive compared to NDVI.