Keynote address 3 seishi

ICT in Agriculture – Lessons learned in Asia

Seishi NinomiyaThe University of Tokyo

Agriculture was successful in 20th century

1961 2003

• Wheat 1.1 t/ha 2.9 t/ha (2.7 times)• Rice 1.9 t/ha 4.0 t/ha (2.1 times)• Corn 1.9 t/ha 4.7 t/ha (2.4 times)

• Population3 billion 6.3 billion (2.1 times)

• Labor (hrs/ha)*1,750 hrs 250hrs (1/7th)

FAO statistics * Case of Japan1 ha = 2.5 acre

But its sustainability is being terrified

• Serious impacts on environment– Water pollution and shortage– Damage on ecosystem– Degradation of soil– CO2 emission in total

• Food safety and reliability issues

because the success depended on chemicals and high resource consumption, resulting in

In addition, climatic change and frequent extreme weather are destabilizing crop productivity

Agriculture in 21st century

• Food shortage crisis– Population increases by 200,000 per day– Usage of food for bio-fuel – Meat consumption increase– Unstable and short water supply– Land shortage and degradation– Damage by global warming and frequent extreme whether

conditions

• Real sustainability of food production– Paradigm shift from maximization to optimization– High productivity– Profit performance– Low impact on environment– Sustainable resource management– Food safety– Robustness and best management against global warming

An example of such optimization

• Reduction of pesticide application results in – Cost reduction

• Material cost, labor cost

– Lower impact on environment– Lower CO2 output– Food safety and reliability

• To reduce pesticide– Timely and pinpoint protection (application)

• For timely and pinpoint protection– Prediction of pest emergence– Optimal crop management

6

ICT helps optimization in many aspects

• Sustainable agriculture– Optimal agro-chemical application– Optimal energy saving

• Cost reduction and competitive agriculture– Optimal farm planning, efficient management of large number of fields– Efficient distribution of products

• Robust and stable farm production under extreme weather and global warming

– Optimal crop / variety recommendation, optimal cropping timing– Early warning system of extreme weather

• Food safety and reliability– Tractability, right use of pesticide– GAP risk management

• High quality products– Quality sensing and optimal crop management

• Acceleration of agricultural research

Challenges in technologies

• Site-specific data acquisition– Spatially high resolution data– Efficient ground data monitoring

• Decision model tuning/assimilation and evaluation

• Agricultural cloud to share data and applications– Platform to exchange data seamlessly

• Spatial and temporal data integration• Data standardization• Multilingual system to share data among countries and

regions

Integration of low cost sensor networks

JICA Project, Beijing

Coffee farm, Hawaii

University of Florida

Rain fed paddy, Khon Kaen

Spinach farm, Chengmai Tomato green house

Orange farm, Arida Orange farm,

kumano

Rice paddy, NARC

Pasture Imja Glacier Lak, Nepal

A farm, Hokkaido

http://yummy.narc.affrc.go.jp/fieldserver/monitor/default.htm

Immigration Route

4 mm

3 mgRice Hopper

Airborne pest immigration prediction – an example of data integration

• Weather forecast to predict stream speed and direction

• Particle diffusion model to predict insect dispersion

• Identification taking-off origin– Inverse simulation based on insect trap data to find

candidates locations of origins

– Satellite image analysis to identify paddies of origins among candidates

– Crop growth model to estimate rice growth stage

• Insect behavior model to estimate taking-off time

Global scale rice productivity simulation

The last one mile issues

• Lingual illiteracy– How to communicate with them?

• ICT illiteracy– How to extend ICT in rural area?

• Lack of site-specific information– How to provide it for most optimal site-specific decisions?

• Shortage of extension staffs– Who provides proper advices?

• Difficulty to realize extensibility of the approach to different language

12

Youth Mediated Communication Model　（ YMC）

• A totally new approach of decision support system to solve the last one mile issues with illiterate farmers

• Communication with illiterate farmers through children being educated at schools

• Site-specific field information acquisition by children

• To compensate the lack of local experts by remote experts

• An way to extend ICT in rural area through educating children

• A trial to provide internationally extensible mechanism

YMC Viet general flow

[1] Hearing

[3] Reply[4] Communicating reply from expert

[2] Write Qs　　 Field Data　

Dialogue with Experts(via Internet)

Analogue communication

Copyright © 2011 NPO Pangaea

Test bed in Vietnam40 families participatedChildren from age 9 to 14

Sensor tools used in YMC Viet


Children sensors in action

Air temperature and humidity

15

Plant height, leaf color, pests

Plant images

Youth Flow 1/2


Youth Flow 2/2


Q & A mechanism

• Typical questions and corresponding answers are provided in advance as a Q & A sets– About 250 sets at the beginning

– So-called recipe cards are provided corresponding to typical answers

– Qs & As are not simply one-to-one so that experts need to interact

• Children can also consult experts with free text questions when they cannot find proper ones in the Q&A sets– The interactions between children and experts are used to

enrich the Q&A sets

• Questions go along with field data by children

Recipe Cards for easier communication

Cards are used to tell parents about experts advices as it

is easy to forget by the time you go home.


Information Flow of YMC

Experts in Japan and Vietnam

YouthPC

Mobile phone

illiterate famers

Question and field information・

Answer

Question

Answer

Machine translation

Service Grid

Analogue tools

Bridger

Support translation

Facilitator・ Support children・

Rural Area

YMC System(Q&A system+ online text)


Some photos taken by youths

• Youths’ sensors will provide spatially high density weather information– Low cost and maintenance free– Outlier can be easily found– Very useful for reliable decision support

• The collected data can be used for an early warning system– e.g. Emergence of rice blast– GIS can be a good interface

• Long-term continuous observation makes decision support more reliable– By overcoming site-specificity of agriculture

Youth Sensors

Plant height data reported by children

Conclusions

• YMC approach seems to work fine in advising illiterate farmers though we need to continue the trial for some more cropping seasons to give the evaluation

• Youths’ sensors help the experts to provide proper advices

• Children became more interested in agriculture than before and have more communication with parents

27

Seishi Ninomiya　 [email protected]

Thank you very much

Agriculture and world population

6 5 4 3 2 1 10 10 10 10 10 10

7

10

　 4

10

10

10

15000

5million

0.5billion

6.5billion 　

Agriculture

Tools (implements and fire)P

op

ula

tio

n

Years ago　 Revised from Robert W.Kate(1994)

20th century

Keynote address 3 seishi

Technology

Transcript of Keynote address 3 seishi