Maize Baseline#
This section compares three different fertilization policies used in an experiment to improve crop yield.
The first policy is the “null” policy, which involves no fertilizer application, and is used as a reference point to measure the effect of nitrogen fertilizer on crop yield.
The second policy is the “expert” policy, which is the fertilizer application policy used in the original experiment.
The third policy is a “PPO” policy, learned with default hyper-parameters.
Note
The PPO policy was trained for \(10^6\) episodes with stochastic weather generation, and the best model was saved based on performance in a validation environment. The performance of each policy was measured with \(10^3\) episodes in a test environment; featuring different stochastic weather series from those used in training and evaluation environments of PPO, to avoid over-optimistic performance measures.
Training and evaluation code can be found in the following repository.
Caution
The results may be slightly different than the report due to stable-baselines3 different version and DSSAT engine update.
Policy |
Grain Yield (kg/ha) |
Massic nitrogen in grains (%) |
Total Fertilization (kg/ha) |
Application Number |
Nitrogen Use Efficiency (kg/kg) |
---|---|---|---|---|---|
Null |
1089.7 (369.8) |
1.1 (0.1) |
0 (0) |
0 (0) |
n.a. |
Expert |
3636.3 (1903) |
1.6 (0.3) |
115.8 (5.2) |
3 (0.1) |
22 (14.3) |
PPO |
3535.3 (1813.7) |
1.5 (0.2) |
98.7 (21) |
3.5 (1.2) |
25.5 (16.7) |