Hybrid-Physical Probabilistic Forecasting for a Set of Photovoltaic Systems using Recurrent Neural Networks

Accurate intra-day forecasts of the power output by PhotoVoltaic (PV) systems are critical to improve the operation of energy distribution grids. We describe a hybrid-physical model, which aims at improving deterministic intra-day forecasts, issued by a PV performance model fed by Numerical Weather Predictions (NWP), by using them as covariates in the context of an autoregressive recurrent neural model. Our proposal repurposes a neural model initially used in the retail sector, and discloses a novel truncated Gaussian output distribution. We experimentally compare many model variants to alternatives from the literature, and an ablation study shows that the components in the best performing variant work synergistically to reach a skill score of 7.54% with respect to the NWP-driven PV performance model baseline.

Transfer Learning of Photometric Phenotypes in Agriculture Using Metadata

Estimation of photometric plant phenotypes (e.g., hue, shine, chroma) in field conditions is important for decisions on the expected yield quality, fruit ripeness, and need for further breeding. Estimating these from images is difficult due to large variances in lighting conditions, shadows, and sensor properties. We combine the image and metadata regarding capturing conditions embedded into a network, enabling more accurate estimation and transfer between different conditions. Compared to a state-of-the-art deep CNN and a human expert, metadata embedding improves the estimation of the tomato's hue and chroma.