Big data matters Sensors Mathijs Vonder

1. Sensors Going Smart
Smart Farming
1
Matthijs Vonder
• 1986 - 1992 UT-Electrotechnics
• 1992 - 1994 UT-Mechatronics (TWAIO)
• 1995 - 1998 Buhrs Zaandam
• 1998 - 2002 KPN Research
• 2003 - now TNO
Sr. Technical Scientist
Group: Monitoring & Control Services
Role: IT-Architect, Project leader
Large Scale (Infrastructure) Monitoring
• IJkdijk / Floodcontrol / Earthquakes
• SmartDairyFarming 1, 2, 3, (a.o. Young
Stock Rearing)
• Data Intensive Smart Agriculture Chains
(DISAC) – E-pieper
• IoT / Big Data (architectures/DDA)
matthijs.vonder@tno.nl
Contents
Introduction and positioning
Precision Dairy Farming
Data Sharing (via InfoBroker concept)
Some developments
Messages

2. Introduction and positioning
PF = Precision Farming (animals + agriculture )
PLF = Precision Lifestock Farming (animals, e.g pigs, poultry, cows)
PDF = Precision Dairy Farming (milk cows)
Project Smart Dairy Farming (SDF)
that is about PDF
Goal of project SDF1:
to support dairy farmers in the care of
individual animals.
with the specific goal of a longer
productive stay at the farm due to
improvement of individual health.
2
aka Smart
Farming

3. Starting point:
Cow centric thinking
Starting point:
Farmer in control
“De boer aan het roer”
Real time models / services
(at different providers)
Sensors from
different suppliers
Other data
sources
InfoBroker: Open platform
for (sensor) data producers
and consumers
Cow specific
workinstruction
(SOP)
Precision Dairy Farming
3

4. Some SDF1 – Facts & Figures
4
Farm 1 Farm 2 Farm 3 Farm 4 Farm 5 Farm 6 Farm 7
# cows/calves 459 186 315 239 706 202 351
Behaviour
Temperature
Activity
Milk production
Feed intake
Weight
Water intake
Milk intake
NB1: blue numbers are animals; not all animals are monitored for SDF (e.g. 3 and 4 only calves)
NB2: the left column gives a list of “sensor data categories” at a farm
NB3: numbers in black are the sensor fields within a category (e.g. 3 fields related to waterintake)
Farm 1 Farm 2 Farm 3 Farm 4 Farm 5 Farm 6 Farm 7
# cows/calves 459 186 315 239 706 202 351
Behaviour 5x 5x
Temperature 1x 1x
Activity 9x 9x 3x 6x 5x 13x 9x
Milk production 16x 20x 1x 2x 19x
Feed intake 24x 24x 10x 24x
Weight 10x 6x 6x 6x 7x 6x 10x
Water intake 3x 3x
Milk intake 7x 11x
See next
slide

5. Examples: young stock
5
Waterintake
life_number
date_time
Sensor
Tiks
daytikscounter
Weight
life_number
date_time
Sensor
Wcorr
Wstable
Wzero
Wavgmin
Wavgmax
Milkintake
life_number
date_time
Sensor
soll
soll_rm
abruf
SAUG
abbr_oz
besuch_ot
besuch_mt

6. Starting point:
Cow centric thinking
Starting point:
Farmer in control
“De boer aan het roer”
Real time models / services
(at different providers)
Sensors from
different suppliers
Other data
sources
InfoBroker: Open platform
for (sensor) data producers
and consumers
Cow specific
workinstruction
(SOP)
Precision Dairy Farming
Think big,
start small
6
Numbers for the Dutch situation:
• 15000+ farmers
• in total more then 1.5 million milk cows
• 20 to 200+ datafields per cow
• many different stakeholders in the chain

7. 7
Data Sharing: InfoBroker concept
InfoBroker* functionalities:
Open interfaces for data exchange (API)
Authentication
who are you (are you allowed to login)
Permissions
which data may be used by whom
to be set by the farmers
Namingservice
location where the data can be found
Integration
combining info from different sources
Pay-per-use
fixed costs (connections)
variable costs (used data)
So:
no central datastore for (sensor)data!
but indeed a broker
and reduces/prevents duplication
cow specific work
instructions (SOPs)
InfoBroker
cow centric data
cow centric
data
Cow centric
Sensor data
Static data
(e.g. feed)
Cow centric
Sensor data
Static data
(e.g. date of birth)
Dashboard
Model
Model
Model
x 15.000+
* For InfoBroker see eg. EC-PLF paper (Vonder, van der Waaij, Harmsma, & Donker, 2015)
publications.tno.nl/publication/34623333/DBpkjn/vonder-2015-near.pdf

8. Some scenario’s for using the InfoBroker:
InfoBroker
Realtime-Model
(expert)
Farmer
What else?BenchmarkingCoöperation
Advisor
Static
data
Real time
cow-centric
data
8
GovernmentOther farmers

9. Some Smart Farming / Big (sensor) Data
developments (at TNO)
Big Data IT-architectures
For Multi Stakeholder Collaborations
from Research to Operations: “Think Big, Start small”
Semantic interoperability of (sensor) data
Linked Data, Ontology mapping, etc
Eg. Common Dairy Ontology (CDO)
Data Driven Analyses (DDA)
E.g. “roughage intake prediction”, “look-alike-cow”,
“pregnacy insemination failure prediction”
Interactive Visualisation of BD
Dashboards, pixel plots, etc
Virtual/Augmented reality (Hololens)9
Cooperatie Datahub
Operational implementation of InfoBroker,
permissions and more (live Q4 2017)

10. Messages
Use of sensor (and other) data (via an InfoBroker/Datahub) could be the
right direction for statistical products
Improve current statistics
Develop new statistics
Lower the response burden
A lot of data is already/soon available, for Dairy e.g.
Static and sensor data of dairy cows
Pasture behaviour-, financial-, environmental data
And more agrifood sub domains to come soon
Think about: What-is-in-it for the data-owner (e.g. farmer)?
Money (for the data)?
Lower response burden?
Benchmark-report (relative position compared to peers)?
O
One liner: Think Big, Start small !
Start experimenting now (and give feedback for additions/improvement)!
Work together with others (Multi Stakeholder Collaboration)
10

11. Thank you for your attention
info: matthijs.vonder@tno.nl
For more inspiration:
TIME.TNO.NL