data mining to combine sensor information to improve oestrus detection
TRANSCRIPT
Modelling in the SDF projectCase: improve heat detection by combining sensor data
Claudia Kamphuis, Wageningen UniversityKirsten Huijps, CRVPieter Hogewerf, Wageningen Livestock Research
Content
- The Why and What of Smart Dairy Farming
- Fertility and heat detection
- Where to from here
SDF: Why & What
Improve a cow’s productive lifetime by putting the famer and the cow in the
centre
Three processes that are difficult to manage but that will increase
productive lifetime
Collaboration between commercial companies, research centres,
universities and FARMERS
Develop decision support models, management tools and advisory products that contribute to an increased productive lifetime
SDF: Fertility Project
- Importance of fertility- A cow needs a calf to produce milk- Goal to get cows pregnant fast- Key drivers: detection and insemination
-Current challenges- Time consuming - Recording- Increased herd sizes
SDF: Fertility Project
- Automated heat detection: a success story- Automated heat detection: a success story...when it all works
SDF: Fertility Project GOAL
Improve automated heat detection by using all available dataProvide insemination advice (bull information, timing)Generate follow-up listsGenerate calving attentions
Data collection in the fieldTwo commercial farms in ‘Friesland’
• 250 cows• 2.5 fte
• 450 cows• 4.5 fte
820-8-2015
Farm 1Yield, Weight, Feed intakeevery milking (24/7)
Activity (alerts), Rumination every 2h
Collection since June 2013- Manual recording of heat observations- Continuous automatic recording of sensor data
Activity (alerts) every hour
Yield every day
Activity, Eating, Feeding,Ruminating, every hour
Lactation, calving dates, every 4wks
Difficulties in data collection
Action Farm 1 Farm 2Combining sensor data streams (2h blocks)
617,000 788,000
Adding observed heat events 398 events203 cows
477 events236 cows
Develop predictive variables from all raw sensor data
60 105
Develop Logitboost model 398 events398 GS+
20000 GS-
121 events441 GS+
11,032 GS-
Validate model using April 2014 63 events63 GS+
111,186 GS-
24 events72 GS+
22,371 GS-
Mining a predictive model
Preliminary results
Model GS positive Sensitivity (%)
False positives per day
One sensor 63 44 2.5
Combined 63 75 2.8
Model GS positive Sensitivity (%)
False positives per day
One sensor 24 92 2.2
Combined 24 96 1.1
Heat tab
List of cows that were detected as ‘in heat’
Where to from here?
From modelling to near real-time 4 times a day
Per individual cowbest insemination timebull advicetime left for insemination
Where to from here
Near real-time on Farm 2Fine-tune current models
200 farmers across The Netherlands in 2015X different combinations of sensing systemsX number of new detection models
Scaling up
-Smart Dairy Farming: why and what
-Importance of (automated) heat detection- Improve detection by combining sensor data- SDF-Model appears to have potential- SDF-Model is running near real-time ‘as-we-speak’
-Future work- Near real-time Farm 2- Fine-tuning models- Scaling up
Where to from here