SoLIM: An Effort Moving DSM into the Digital Era

Overview and Recent Developments

A-Xing Zhu1,2

1 Department of Geography University of Wisconsin-Madison

azhu@wisc.edu

2 Institute of Geographical Sciences and Natural Resources Research

Chinese Academy of Sciences

Global Soil Partnership: March 20-23, Rome, Italy

OUTLINE Overview

Background Components Application and assessment

Effective sampling New covariates Relaxing the traditional constraints Up to date software implementation

Recent Developments

Current Efforts (into the digital era) Theoretical: Overcoming the tradition constraints Computational: Overcoming the digital divides

Observations (what might be next for GSP?)

Background

SoLIM stands for Soil-Land Inference Model

An approach of using geographic information processing techniques and artificial intelligence techniques to predictively and digitally map soils under fuzzy logic at pixel level

Overview

Originally, it was designed to overcome the limitations of traditional soil survey (manual and its variants): The polygon-soil type (area/class) model and manual delineation.

A joint effort by the United States Department of Agriculture, University of Wisconsin-Madison, the Chinese Academy of

Sciences

Components The similarity model - overcoming the limitations of

“polygon-soil type” model

Overview

Sij (Sij1, Sij

2, …, Sijk, …, Sij

n)

j

i Zhu, A.X. 1997. Geoderma, Vol. 77,

pp. 217-242.

Components Inference - overcoming the limitations of manual

delineation and the like

Overview

Inference (under fuzzy logic)

Knowledge on Soil and Environment Relationships

Covariates: cl, pm, og, tp, …

G.I.S./R.S.

Local Experts’ Expertise

<= f ( E )

j

i S

Machine Learning

Case-Based Reasoning

Spatial Data Mining

Zhu, A.X. 1999, IJGIS; Zhu et al., 2001, SSSAJ; Qi and Zhu, 2003, IJGIS; Shi et al., 2004, SSSAJ; Qi et al., 2008, Cartography and GIS;

More at solim.geography.wisc.edu

Overview

Zhu et al., 1997, SSSAJ; Zhu et al., 2010, Geoderma More at solim.geography.wisc.edu

Applications and Assessment Products - Basic output: Fuzzy membership maps

Overview

Raster Soil Type (Series) Map

Applications and Assessment Products - Basic output: Fuzzy membership maps Derived products and accuracy:

Raster soil type maps

Accuracy of the Raster Soil Map

Sample Size = 99

Overall In Complexes In Single

SoLIM

Soil Map

83.8%

66.7%

89%

73%

81%

61%

SoLIM

Soil Map

24

4

30

30

80%

13%

Mismatches

Correct Total Mismatches Percentage

Comparison between SoLIM and Soil Map against field data (Raffelson)

Overview

Zhu, A.X. 1997, Photogrammetric Engineering & Remote Sensing, Vol. 63, pp. 1195-1202

Applications and Assessment Products - Basic output: Fuzzy membership maps Derived products and accuracy:

Raster soil type maps; Uncertainty Map

Applications and Assessment Products - Basic output: Fuzzy membership maps Derived products and accuracy:

Raster soil type maps; Uncertainty map Soil property map

Overview

Zhu, A.X. 1997, Photogrammetric Engineering & Remote Sensing, Vol. 63, pp. 1195-1202

A-Horizon Depth from SoLIM A-Horizon Depth from the Soil Map

0

5

10

15

20

25

30

35

0 5 10 15 20 25 30 35

Observed Depth (cm)

Dep

th b

ased

on

Sim

ilari

ty V

ecto

r (c

m)

R2 = 0.602 N = 33

Depth Based on SoLIM vs.

Depth from the Field

0

5

10

15

20

25

30

35

0 5 10 15 20 25 30 35

Observed Depth (cm)

Dep

th fr

om S

oil M

ap (c

m)

R2 = 0.436 N = 33

Depth From the Soil Map vs.

Depth from the Field

Applications and Assessment Products - Basic output: Fuzzy membership maps Derived products and accuracy:

Raster soil type maps; Uncertainty map Soil property map; Uncertainty map

Overview

Effective sampling Recent Developments

What if no soil data (no soil field experts, no soil maps, no soil samples)?

Sampling!!! Random or Regular? But the question is: Can we do smart sampling?

Purposive sampling: Through spatial analysis sampling locations and sampling order are prioritized in such a way to make sampling more effective (fewer in number and integral from different campaigns).

Zhu et al., 2010, Geoderma; Yang et al., 2012, IJGIS

No. of Samples MAE RMSE Purposive sampling 7 0.82 1.05 Linear regression

model 41 1.18 1.48

Effective sampling New covariates

Recent Developments

Dynamic feedback patterns from remote sensing data

Stimulate Feedbacks

地表Land surface

Produce

地表反馈Land surface

dynamic feedbacks

降雨Rainfall

Input

Stage 1

Capture and Characterize Feedbacks

Obtain

Multi-temporal and multi-spectral dataset

ObserveMODIS传感器MODIS sensors

Stage 2Extract relationships with soils

Identify Soil dataSoil data

响应模式差异

与土壤差异的关系

Relationships between response patterns and soil types

Discover Spectral-temporal response patterns

Stage 3

Zhu et al., 2010, SSSAJ; Liu et al., 2012, Geoderma

Effective sampling New covariates

Recent Developments

Dynamic feedback patterns from remote sensing data Fuzzy slope positions

Qin et al., 2009, Geomorphology; Qin et al., 2012, Geoderma

Summit

Slope

Valley

……

Effective sampling New covariates Relaxing the traditional constraints How to use ad-hoc samples (few in number and spatially biased samples) Individual Representativeness Approach

Recent Developments

Each sample is representative to some region in the feature space

elevation

precipitation

parent material

samplek

No data

Organic matter content (top soil) Uncertainty Map

0

1

2

3

4

5

6

7

0.00 0.05 0.10 0.15 0.20 0.25

不确定性

推测残差

Res

idua

l

Uncertainty

Effective sampling New covariates Relaxing the traditional constraints Up to date software implementation

Recent Developments

SoLIMSolutions2010 contains most of the above developments and also a help manual. Available at solim.geography.wisc.edu

Current Efforts (into the digital era) Theoretical: Overcoming the tradition constraints

Integration of: Soil scientist knowledge Legacy data (maps and sample points) Ad-hoc field samples

Estimation of uncertainty Uncertainty guided sampling

Unc

erta

inty

Order of “Optimal” Samples

Progressive Mapping

Current Efforts (into the digital era) Theoretically: Overcoming the tradition constraints Computationally: Overcoming the digital divides

Multiple Cores

Computing Clusters

Cloud Computing

Single Core Specialists

Geospatial Analysis &

Digital Soil Mapping

H.P. Computing Enabled

Complex Computing

Enabled

Intuitive Model Building

Assisted Model Building

Cyber Sharing

To Use

To Com

pute

Platform

EASY

Geographic Computing (easy GC)

Current Efforts (into the digital era)

easyGC (prototype) - for non-specialists

Observations (what might be next for GSP?)

Coordinated but distributed efforts with capacity building being the focus

Distributed efforts: each member country responsible for its own country Coordinated: FAO has a mandate to do that (as part of its mission

statement, I believe) Capacity building: Training of the new technology Development of easy to use technology

Thank your for your attention!

Contact: A-Xing Zhu Department of Geography University of Wisconsin-Madison azhu@wisc.edu Web Site: solim.geography.wisc.edu