Fig. 14
Results of the simple feed-forward neural network used to estimate maize yields based on annual timeseries of GOSIF27 observations (Fig. 13). The neural network is trained and tested on the Africa-wide ground-truth dataset shown in Fig. 11. The testing data represents a random 20% of the dataset not used to train the model. The value ρ(x, y) denotes the correlation coefficient between the predicted yield from the neural network and the government-reported yield. Due to the large number of data points, the data are grouped into equally-spaced bins and are represented based on their binned mean values (squares), 25-75th percentiles (thick lines), and 10-90th percentiles (thin lines).
