Remote Sensing and GIS for Agriculture Supply Chain Management

1
Remote Sensing and GIS for Agriculture Supply
Chain Management

• Presented on behalf of
• Dr. K.S.Siva Subramanian

2
Understanding Supply Chain Management Role of RS
3
What is Supply Chain management?
Flow of Material, Money, Knowledge Information
Product from producers or Growers to Users or
market
Government bodies, Industries, Commercial group,
middlemans etc
R D Initiatives, Technology transfer etc
Information required by Agri. sector
Info on type and quality of crop
Info on location and quantity of crop
Info on what needs to be improved and how?
4
Agriculture Information in Supply Chain
Agriculture Landscape in Supply Chain management

• Agriculture Market Structure
• Growers and their challenges
• Productivity of crop
• Problems of price realization
• Availability of quality inputs
• Tribulations such as flood, drought, food
  insecurity
• Middle man domination

Organized Market
Unorganized Market

• Greater flow of information
• Market more transparent
• Commodity exchanges
• Cultivation/Manufacturing based commodities

• Staggered flow of information
• Market less transparent
• Collection based commodities

5
Information link in Agriculture Supply Chain
Information type in Agriculture Supply Chain
Management

• Information on
• Acreage Spatial distribution of crop
• Type of crop
• Health of crop
• Yield and production forecasted information

Agriculture Intelligence data
6
Utility of Agriculture Intelligence Data
Utility of Agriculture Intelligence Data

• AI Data users
• Industries for procurement and supply chain
  management
• Agriculture Boards to streamline supply chain
  and fix price in market
• Insurance Company to create insurance products

Middleman
Grower
User
7
Agriculture Intelligence Data Sources

• Initiatives through
• Agencies
• APEDA (Agriculture and Processed Food Products
  Export Development Authority)
• AGMARKNET (Agriculture Marketing Network)
• MCX (Multi Commodity Exchange)
• CSE (Commodity Stock Exchange)
• more..
• Research Institutions
• NIAM (National Institute of Agricultural
  Marketing)
• ICAR (Indian Council of Agricultural Research)
• more..

8
Agriculture Intelligence Data Sources

• Programmes
• CAPE (Crop Acreage and Production Estimation)
• FASAL (Forecasting Agricultural output using
  Space, Agro-meteorological and Land based
  observations)
• Federal Agricultural department - Field sampling
  surveys
• Industrial houses - Field sampling
• Agencies like Agriwatch, CSE are also gathering
  AI data using multiple filed sources

• Variations in Information
• No Single Source of Data
• Timelines

9
Advance Technology in SCM

• Role of Remote Sensing in SCM is to
• Generate near real time data
• Validation
• Accuracy Improvement
• Time and Cost effective solution

10

• Agriculture Intelligence Data Creation for Supply
  Chain Management

11
Agriculture Intelligence Data Creation for SCM
AI INFORMATION AI INFORMATION
AREA COVERED PARAMETERS COLLECTED
Major growing parts /districts Location of mandis / markets Mandi/ Market Arrival Data Time of Arrival Approximate estimates
DATA
12
Agriculture Intelligence Data
Agriculture Intelligence Data Creation for SCM
13
Key Components of GIS Development
Agriculture Intelligence Data Creation for SCM

Yield production forecasting
Crop health monitoring insurance product
GIS LAYER (Decision Making)
Location mapping acreage estimation
DATA
Block/Tehsil wise data integration and analysis
14
Key Components of GIS Development
Agriculture Intelligence Data Creation for SCM
15
AI data Business Intelligence Layer Development
Agriculture Intelligence Data Creation for SCM
Value added task - interactive Business
Intelligence Layer depending upon specific
requirements.
Platform
GIS LAYER
DATA
16
AI Data Validation
Agriculture Intelligence Data Validation for SCM

• Conventional ways
• Second level sample surveys
• Crop cutting experiments
• GPS validation Error matrix

• Comparison / validation from other sources of
  data
• State marketing boards of respective states
• Agents (Arthias)
• Analysis, discussions with rice millers

17
Agriculture Intelligence Data Validation for SCM
18
Summary

• Benefits
• Rs can play vital role in linking information
  from grower to user
• Traders / growers to rely on middlemen
• RS based data generation and forecasting also
  vital for insurance product
• Geospatial based supply
• Limitations
• Gaps and unorganized secondary data
• Cloud free satellite data especially during
  Kharif season

19

• Agriculture Intelligence Data created as part of
  SCM

20
AI data for Agriculture Industry

• Crop
• Rice
• States Covered
• Punjab, haryana, Uttar Pradesh, Uttarakhand
  Jammu-Kashmir
• Satellite based acreage estimation
• Satellite derived NDVI based yield estimation
• Accuracy checking of estimated production by
  Mandi arrivals and analysis
• Crop health monitoring Based on field surveys and
  satellite images
• Questionnaire based farmer survey

21
AI data for Insurance Company

• Crop
• Wheat in 13 Districts in Punjab, Haryana,
  Rajasthan, UP
• Scope of the Study
• Crop mapping
• NDVI estimation
• Generation of block level weighted mean NDVI
  statistics
• Deliverables
• Block wise weighted mean NDVI statistics
• NDVI range map

2006-07
Subset FCC of Project District of Punjab
Wheat Classified Map of Project District of
Punjab
NDVI Map of Project District of Punjab
NDVI Range Map of Project District of Punjab
22
Stress Analysis for Multiple Crops
AI data for Insurance Company

• Crop health based AI data
• Crop Stress Mapping Analysis
• Jowar, Wheat, Gram Onion
• Study Area
• Satara Solapur Dist. of Maharashtra

23
Ai Data for Government Board

• Crop
• Coconut Plantation
• AI data created
• Coconut plantation mapping
• Acreage estimation
• Yield estimation
• Stress areas mapping
• Study area
• Coimbatore District, TN
• Kasargod and Kollam Districts, Kerala

Land use/ Land cover Map
Coconut Plantation Map
IRS LISS III FCC
24
Delivering a world of solutions

• info_at_rmsi.com
• www.rmsi.com