Spatial Modeling of a Soil Fertility Index using Visible–Near‐Infrared Spectra and Terrain Attributes

Soil Science Society of America Journal - Tập 74 Số 4 - Trang 1293-1300 - 2010
Raphael A. Viscarra Rossel1, Rodnei Rizzo1,2, José Alexandre Melo Demattê2, Thorsten Behrens3
1CSIRO Land and Water, Bruce E. Butler Lab., GPO Box 1666, Canberra, ACT, 2601 Australia
2Soil Science Dep. Univ. de São Paulo Piracicaba S.P. Brazil
3Institute of Geography, Physical Geography, Univ. of Tübingen Rümelinstraße 19‐23 D‐72074 Tübingen Germany

Tóm tắt

Our objective was to develop a methodology to predict soil fertility using visible–near‐infrared (vis–NIR) diffuse reflectance spectra and terrain attributes derived from a digital elevation model (DEM). Specifically, our aims were to: (i) assemble a minimum data set to develop a soil fertility index for sugarcane (Saccharum officinarum L.) (SFI‐SC) for biofuel production in tropical soils; (ii) construct a model to predict the SFI‐SC using soil vis–NIR spectra and terrain attributes; and (iii) produce a soil fertility map for our study area and assess it by comparing it with a green vegetation index (GVI). The study area was 185 ha located in São Paulo State, Brazil. In total, 184 soil samples were collected and analyzed for a range of soil chemical and physical properties. Their vis–NIR spectra were collected from 400 to 2500 nm. The Shuttle Radar Topographic Mission 3‐arcsec (90‐m resolution) DEM of the area was used to derive 17 terrain attributes. A minimum data set of soil properties was selected to develop the SFI‐SC. The SFI‐SC consisted of three classes: Class 1, the highly fertile soils; Class 2, the fertile soils; and Class 3, the least fertile soils. It was derived heuristically with conditionals and using expert knowledge. The index was modeled with the spectra and terrain data using cross‐validated decision trees. The cross‐validation of the model correctly predicted Class 1 in 75% of cases, Class 2 in 61%, and Class 3 in 65%. A fertility map was derived for the study area and compared with a map of the GVI. Our approach offers a methodology that incorporates expert knowledge to derive the SFI‐SC and uses a versatile spectro‐spatial methodology that may be implemented for rapid and accurate determination of soil fertility and better exploration of areas suitable for production.

Từ khóa


Tài liệu tham khảo

Awiti A.O., 2007, Soil condition classification using infrared spectroscopy: A proposition for assessment of soil condition along a tropical forest–cropland chronosequence, Geoderma, 143, 73, 10.1016/j.geoderma.2007.08.021

Behrens T., 2009, Multi‐scale digital terrain analysis and feature selection for digital soil mapping, Geoderma, 55, 175

10.1016/j.geoderma.2005.04.025

Catani R.A., 1955, Avaliação da exigência em calcário dos solos do Estado de São Paulo mediante correlação entre pH e a porcentagem de saturação em bases, Rev. Agric. Piracicaba, 30, 49

Cesar M.A.A., 1987, Capacidade de fosfatos naturais e artificiais em elevar o teor de fósforo no caldo de cana‐de‐açucar visando o processo industrial, STAB: Acúcar, Álcool Subptodutos, 6, 32

10.2136/sssaj2001.652480x

Ciotta M.N., 2003, Soil organic matter and cation exchange capacity increases in a low activity clay soil under no‐tillage system. (In Portuguese, with English abstract.), Cienc. Rural, 33, 1161

De Camargo A.O., 1986, Chemical, physical and mineralogical analyses methods of the IAC soils

10.1016/j.geoderma.2003.09.012

10.1080/02693799508902047

Girgin B.N., 2005, Landscape position and surface curvature effects on soils developed in the Palouse area, Washington, Proc. SPIE, 2818, 61, 10.1117/12.256077

10.1007/978-0-387-21606-5

Jarvis A., 2008, SRTM 90m digital elevation data, version 4

10.1097/00010694-194111000-00009

Lespch I.F., 1987, Ecofisiologia da produção, 83

Letey J., 2003, Deficiencies in the soil quality concept and its application, J. Soil Water Conserv., 58, 180

Malet P., 1996, Classifying the geometry of canopies from time variations of red and near infrared reflectance, Remote Sens. Environ., 56, 164, 10.1016/0034-4257(95)00223-5

10.1590/S0103-90162001000200012

10.1016/S0016-7061(03)00223-4

10.2136/sssaj1996.03615995006000060038x

10.1002/hyp.3360050103

10.1016/j.geoderma.2004.09.013

10.1016/j.compag.2006.12.011

10.2136/sssaj2001.1787

Prado H., 2005, Brazilian soils: Genesis, morphology, classification, mapping and management

Prado H., 1998, World Congr. of Soil Sci., 232

Quinlan J.R., 1993, C4.5: Programs for machine learning

10.1016/j.geoderma.2006.03.021

Soil Survey Staff, 1999, Agric. Handbk. 436

10.1016/j.ecolind.2007.05.005

Vagen T., 2005, Sensing landscape level change in soil fertility following deforestation and conversion in the highlands of Madagascar using vis‐NIR spectroscopy, Geoderma, 133, 281, 10.1016/j.geoderma.2005.07.014

Raij B., 1991, Fertilidade do solo e adubação

Raij B., 1983, Bol. Téc. 81

10.1016/j.chemolab.2007.06.006

10.1016/j.geoderma.2009.01.025

10.1016/S0016-7061(98)00023-8

10.1016/j.geoderma.2006.07.004

10.1016/j.geoderma.2005.03.007

Webster R., 2001, Geostatistics for environmental scientists

Thông tin
Thông tin xuất bản

Soil Science Society of America Journal

Tập 74 Số 4

1293-1300

Thông tin tác giả