Crop Yield Prediction
EOSDA team of data scientists and engineers has developed effective techniques for crop yield estimation using remote sensing and machine learning models. We’re relying on earth observation data retrieved from satellites to cover areas ranging from individual farms to regions.
Crop Yield Prediction in Numbers
Accuracy of yield estimated depends on the quality of statistical data and can vary from 85% to 95%.
Current season yield forecasts up to 3 months in advance.
Yield predicted for over 100 crop types.
We’ll produce a 95% accurate yield forecast in two weeks or less, depending on the complexity of the project.
WOFOST yield estimation model requires no data at all.
We make sure the forecasts are based on the most comprehensive data analysis.
Yield Estimation Benefits
- Increased speed of decision-making related to harvesting, storing, and transporting operations.
- Data on crop profitability in your area of interest based on yield estimation.
- Opportunity to strengthen global food security by introducing crop yield forecasting to developing countries - helping them to prevent famine, boost local economies, and implement sustainable agricultural practices.
- Improved understanding of the agricultural market and better-informed decisions on the management of stocks, imports, and exports, in accordance with CAP and other similar policies.
- A much better understanding of cumulative effects of hostile field conditions (pests, diseases, nutrient deficiencies, and others) on crop development.
Our Approach
For maximum efficiency and accuracy of crop yield forecasting, we fuse two different types of yield prediction models - biophysical and statistical. This "hybrid" approach allows us to take on more complex projects.
Biophysical yield prediction model
- Collect data (weather parameters, soil analysis, crop state, phenological data, etc.).
- Calibrate the model and carry out the LAI assimilation to ensure accuracy of a crop yield forecast in the absence of statistical data and to increase the variability of values.
- Simulate the biological productivity parameters (TAGP, WSO, relative soil moisture, total water consumption, and others) to estimate yield.
- Update the data once every 14 days to increase the accuracy. This has to do with weather updates.
Statistical yield prediction model
- Collecting data to create a crop yield prediction dataset and combining it with possible predictors (rainfall, temperature, humidity, soil type, and others).
- Picking the right ML model for the project - e.g. Linear regression, Random Forest, LightGBM, XGBoost, CatBoost, to name a few.
- Adjusting the model to answer the specific needs of the project in question for best results.
Model fusion stage
The fusion stage is necessary if we want to achieve the highest possible accuracy of 95%. We fuse the biophysical yield prediction model with the statistical model described above.
EOSDA Crop Modeling + LAI Assimilation
-
Ensemble of model scenarios
-
Asquisition 1
-
Asquisition 2
-
Asquisition 3Selection of most likely scenario and re-initalization of the modelled ststem state with the scenario
-
Asquisition 4Observations of LAI
-
Asquisition 5
-
Harvest
Applying LAI assimilation allowed us to achieve the 95% accuracy in 30% of the fields. For the fields marked in red, the accuracy of less than 80% was achieved, while the crop yield forecast accuracy for the green-marked fields exceeded the 80% mark.
Our Success Stories
Yield forecast for a large agroholding in Ukraine
Two different reports were generated:
- 45 days prior to the harvest
- 2 weeks prior to the harvest.
- less than 80% accuracy
- more than 80% accuracy
| Accuracy (Wofost) | Accuracy (Wofost + Lai) | ||
|---|---|---|---|
| Maize | |||
| Maize | 0.75 | 0.91 | |
| Soy | |||
| Soy | 0.78 | 0.86 | |
| Sunflower | |||
| Sunflower | 0.71 | 0.88 | |
| Winter barley | |||
| Winter barley | 0.53 | 0.82 | |
| Winter wheat | |||
| Winter wheat | 0.75 | 0.92 | |
The table below shows the correlation between the accuracy of yield estimation, the target crop and the number of fields. For example, the predicted yield of winter barley was more than 90% accurate for 52 fields.
| Number of Fields | ||||||
|---|---|---|---|---|---|---|
| Crop / Accuracy | ||||||
| Crop / Accuracy | <70% | 70-75% | 75-80% | 80-85% | 85-90% | >90% |
| Winter barley Number of Fields | ||||||
| Winter barley | 27 | 7 | 5 | 22 | 23 | 52 |
| Winter wheat Number of Fields | ||||||
| Winter wheat | 33 | 17 | 19 | 21 | 19 | 102 |
| Winter rapeseed Number of Fields | ||||||
| Winter rapeseed | 26 | 6 | 20 | 14 | 27 | 22 |
| Sunflower Number of Fields | ||||||
| Sunflower | 12 | 11 | 12 | 14 | 19 | 22 |
| Soy Number of Fields | ||||||
| Soy | 28 | 22 | 29 | 58 | 37 | 86 |
Crop yield forecasting for a Canadian insurance company
Goal: Reliable predicted yield data on every customer to reduce insurance risks.
Input data: Over 100 fields on 20 farms.
yield estimation model vs actual yield by crop type given in %
| Crop | Modelled Yield | Actual Yield | |
|---|---|---|---|
| Canola | |||
| Canola | 41,81 | 41,00 | |
| Corn | |||
| Corn | 123,65 | 110,00 | |
| Peas | |||
| Peas | 30,94 | 25,00 | |
| Soybean | |||
| Soybean | 22,89 | 22,00 | |
| Sunflower | |||
| Sunflower | 1767,73 | 1800,00 | |
| Wheat | |||
| Wheat | 53,72 | 53,00 | |
| Grand Total | |||
| Grand Total | 95,6 | 94,47 | |
yield estimation model vs actual yield by crop type given in %
| Crop | Modelled Yield | Actual Yield (Farm 4) |
|---|---|---|
| Canola | ||
| Canola | 40,19 | 39,00 |
| Corn | ||
| Corn | 119,14 | 110,00 |
| Oats | ||
| Oats | 125,03 | 125,00 |
| Rye Fall | ||
| Rye Fall | 64,39 | 75,00 |
| Sunflowers Confects | ||
| Sunflowers Confects | 2063,60 | 1800,00 |
| Sunflower Oils | ||
| Sunflower Oils | 1834,19 | 1800,00 |
| Wheat | ||
| Wheat | 61,73 | 65,00 |
| Grand Total | ||
| Grand Total | 584,34 | 528,00 |
The graph shows the predicted yield for target crops in 3 selected fields in bushel/ha.
-
SE-2-6-28-W1
- Field name
- SE-2-6-28-W1
- Canola
- 58,68
- Corn
- 194,33
- Soybean
- 41,45
- Sunflower Oils
- 2208,85
- Wheat
- 72,49
-
SW-36-7-28-W1
- Field name
- SW-36-7-28-W1
- Canola
- 30,91
- Corn
- 169,49
- Soybean
- 14,42
- Sunflower Oils
- 1146,91
- Wheat
- 46,24
-
W-34-5-27-W1
- Field name
- W-34-5-27-W1
- Canola
- 38,77
- Corn
- 151,58
- Soybean
- 24,71
- Sunflower Oils
- 1476,83
- Wheat
- 59,82
| Field name | Canola | Corn | Soybean | Sunflower Oils | Wheat |
|---|---|---|---|---|---|
| SE-2-6-28-W1 | 58,68 | 194,33 | 41,45 | 2208,85 | 72,49 |
| SW-36-7-28-W1 | 30,91 | 169,49 | 14,42 | 1146,91 | 46,24 |
| W-34-5-27-W1 | 38,77 | 151,58 | 24,71 | 1476,83 | 59,82 |
The harvest period for the target crops in Canada usually lasts from August till September. Knowing this, we were able to forecast yield two months before the harvest, achieving an accuracy of over 82%. The accuracy was steadily increasing as the harvest was approaching until it reached 90% just two weeks prior to the harvest, as had been expected.
EOSDA is a leader in the application of earth observation technologies for business and environmental purposes in 22+ industries, making a special emphasis on agriculture and forestry. So far, over 900 000 customers worldwide have benefited from the EOSDA satellite monitoring products. We are about to launch our own satellite constellation that will provide imagery in 13 spectral channels for agronomists all over the globe. You can task us with crop yield estimation for an area as small as a field and as large as a country. Using 10 separate sources of data along with trained neural network models, our team of RnD scientists will help your business thrive sustainably.
We’re here to help!
Improve your farming experience thanks to a remotely managed agro team of your dream
