High spatial resolution remote sensing and machine learning have improved the accuracy and affordability of high-throughput phenotyping. This paper presents an innovative approach to yield prediction, leveraging multimodal networks and integrating remote sensing data from two sensing technologies. We explore the synergy among different types of remote sensing data, meteorological data, and management practices employing advanced machine learning techniques to enhance accuracy and reliability in yield predictions.This study focuses on three experiments, one in 2021 and two in different environments with distinct management practices in 2022. Hyperspectral, LiDAR and weather-related features served as initial inputs to the LSTM recurrent neural network-based yield prediction models; management practices related categorical variables were concatenated after the time series output from the attention network. In each experiment, 80% of the data was used for training the model and 20% for testing, investigating three deep learning networks:Traditional vanilla stacked LSTM network.Stacked LSTM Network with a temporal attention mechanism.Multi-modal network for the different remote sensing modalities.The attention weights of each time-step were evaluated to determine the importance of each date;All models produced good predictions, but the attention mechanism coupled with the multi-modality network showed the effectiveness of combining multimodal remote sensing data optimally throughout the season and deep learning algorithms in optimizing agricultural decision-making processes. The Attention networks also provided increased interpretability over the growing season, showing flowering time to be the most critical time for the models, which is consistent with field-based trials.

Reducing nitrous oxide (N2O) emissions from agriculture is critical to limiting future global warming. In response, a growing number of food retailers and manufacturers have committed to reducing N2O emissions from their vast networks of farmer suppliers by providing technical assistance and financial incentives. A key challenge for such companies is demonstrating that their efforts are leading to meaningful progress towards their climate mitigation commitments. We show that a simplified version of soil surface nitrogen (N) balance, the difference between N inputs to and outputs from a farm field (e.g., fertilizer N minus crop N), is a robust indicator of N2O emissions. Furthermore, we present a generalized environmental model which will allow food-supply-chain companies to translate aggregated and anonymized changes in average N balance across their supplying farms into aggregated changes in N2O emissions. This research is an important first step, based on currently available science, in helping companies demonstrate the impact of their sustainability efforts.