FoodRL: A Reinforcement Learning Ensembling Framework For In-Kind Food Donation Forecasting

• URL: http://arxiv.org/abs/2511.04865v1
• Date: Thu, 06 Nov 2025 23:08:19 GMT
• Title: FoodRL: A Reinforcement Learning Ensembling Framework For In-Kind Food Donation Forecasting
• Abstract summary: Traditional forecasting models often fail to maintain consistent accuracy due to unpredictable fluctuations and concept drift.<n>We propose FoodRL, a novel reinforcement learning (RL) based metalearning framework.<n>FoodRL can facilitate the redistribution of food equivalent to 1.7 million additional meals annually.
• Score: 8.858171965804912
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Food banks are crucial for alleviating food insecurity, but their effectiveness hinges on accurately forecasting highly volatile in-kind donations to ensure equitable and efficient resource distribution. Traditional forecasting models often fail to maintain consistent accuracy due to unpredictable fluctuations and concept drift driven by seasonal variations and natural disasters such as hurricanes in the Southeastern U.S. and wildfires in the West Coast. To address these challenges, we propose FoodRL, a novel reinforcement learning (RL) based metalearning framework that clusters and dynamically weights diverse forecasting models based on recent performance and contextual information. Evaluated on multi-year data from two structurally distinct U.S. food banks-one large regional West Coast food bank affected by wildfires and another state-level East Coast food bank consistently impacted by hurricanes, FoodRL consistently outperforms baseline methods, particularly during periods of disruption or decline. By delivering more reliable and adaptive forecasts, FoodRL can facilitate the redistribution of food equivalent to 1.7 million additional meals annually, demonstrating its significant potential for social impact as well as adaptive ensemble learning for humanitarian supply chains.

Related papers

• Food-R1: A Unified Multi-Task Food Vision-Language Model with Reinforcement Learning [44.68518637735983]
  We introduce CalorieBench-80K, a large-scale benchmark with curated calorie labels and dietary advice annotations.<n>To the best of our knowledge, it is the first food image benchmark to incorporate Chain-of-Thought (CoT) annotations for calorie reasoning.<n>We also propose Food-R1, a unified food VLM trained in a multi-task learning paradigm to equip the model with broad capabilities.
  arXiv  Detail & Related papers  (2026-06-03T15:07:12Z)
• Leveraging LLMs for Predictive Insights in Food Policy and Behavioral Interventions [1.979158763744267]
  Food consumption and production contribute significantly to global greenhouse gas emissions. Food policy initiatives have explored interventions to reshape production and consumption patterns. This paper demonstrates that a fine-tuned large language model (LLM) can accurately predict the direction of outcomes.
  arXiv  Detail & Related papers  (2024-11-13T12:21:13Z)
• Anticipatory Understanding of Resilient Agriculture to Climate [66.008020515555]
  We present a framework to better identify food security hotspots using a combination of remote sensing, deep learning, crop yield modeling, and causal modeling of the food distribution system. We focus our analysis on the wheat breadbasket of northern India, which supplies a large percentage of the world's population.
  arXiv  Detail & Related papers  (2024-11-07T22:29:05Z)
• From Bytes to Bites: Using Country Specific Machine Learning Models to Predict Famine [0.0]
  This research investigates how machine learning can be utilized to predict and inform decisions regarding famine and hunger crises. Economic indicators were consistently the most significant predictors of average household nutrition.
  arXiv  Detail & Related papers  (2024-09-16T04:23:06Z)
• NourishNet: Proactive Severity State Forecasting of Food Commodity Prices for Global Warning Systems [0.0]
  Price volatility in global food commodities is a critical signal indicating potential disruptions in the food market. FAO previously developed sophisticated statistical frameworks for the proactive prediction of food commodity prices. Our research builds on these foundations by integrating robust price security indicators with cutting-edge deep learning (DL) methodologies.
  arXiv  Detail & Related papers  (2024-06-30T13:43:26Z)
• Automating Food Drop: The Power of Two Choices for Dynamic and Fair Food Allocation [51.687404103375506]
  We partner with a non-profit organization in the state of Indiana that leads emphFood Drop, a program that is designed to redirect rejected truckloads of food away from landfills and into food banks. Our goal in this partnership is to completely automate Food Drop. In doing so, we need a matching algorithm for making real-time decisions that strikes a balance between ensuring fairness for the food banks that receive the food and optimizing efficiency for the truck drivers.
  arXiv  Detail & Related papers  (2024-06-10T15:22:41Z)
• From Canteen Food to Daily Meals: Generalizing Food Recognition to More Practical Scenarios [92.58097090916166]
  We present two new benchmarks, namely DailyFood-172 and DailyFood-16, designed to curate food images from everyday meals. These two datasets are used to evaluate the transferability of approaches from the well-curated food image domain to the everyday-life food image domain.
  arXiv  Detail & Related papers  (2024-03-12T08:32:23Z)
• Forecasting trends in food security with real time data [0.0]
  We present a quantitative methodology to forecast levels of food consumption for 60 consecutive days, at the sub-national level, in four countries: Mali, Nigeria, Syria, and Yemen. The methodology is built on publicly available data from the World Food Programme's global hunger monitoring system.
  arXiv  Detail & Related papers  (2023-12-01T14:42:37Z)
• Stabilizing RLHF through Advantage Model and Selective Rehearsal [57.504894664689]
  Large Language Models (LLMs) have revolutionized natural language processing, yet aligning these models with human values and preferences remains a significant challenge. This challenge is characterized by various instabilities, such as reward hacking and catastrophic forgetting. We propose two innovations to stabilize RLHF training: 1) Advantage Model, which directly models advantage score and regulates score distributions across tasks to prevent reward hacking; and 2) Selective Rehearsal, which mitigates catastrophic forgetting by strategically selecting data for PPO training and knowledge rehearsing.
  arXiv  Detail & Related papers  (2023-09-18T23:06:32Z)
• Long-term drought prediction using deep neural networks based on geospatial weather data [75.38539438000072]
  High-quality drought forecasting up to a year in advance is critical for agriculture planning and insurance. We tackle drought data by introducing an end-to-end approach that adopts a systematic end-to-end approach. Key findings are the exceptional performance of a Transformer model, EarthFormer, in making accurate short-term (up to six months) forecasts.
  arXiv  Detail & Related papers  (2023-09-12T13:28:06Z)
• Forecasting large-scale circulation regimes using deformable convolutional neural networks and global spatiotemporal climate data [86.1450118623908]
  We investigate a supervised machine learning approach based on deformable convolutional neural networks (deCNNs) We forecast the North Atlantic-European weather regimes during extended boreal winter for 1 to 15 days into the future. Due to its wider field of view, we also observe deCNN achieving considerably better performance than regular convolutional neural networks at lead times beyond 5-6 days.
  arXiv  Detail & Related papers  (2022-02-10T11:37:00Z)
• Fine-grained prediction of food insecurity using news streams [9.04748106111465]
  We leverage recent advances in deep learning to extract high-frequency precursors to food crises from news articles published between 1980 and 2020. Our text features are causally grounded, interpretable, validated by existing data, and allow us to predict 32% more food crises than existing models.
  arXiv  Detail & Related papers  (2021-11-17T17:35:00Z)
• Cross-Modal Food Retrieval: Learning a Joint Embedding of Food Images and Recipes with Semantic Consistency and Attention Mechanism [70.85894675131624]
  We learn an embedding of images and recipes in a common feature space, such that the corresponding image-recipe embeddings lie close to one another. We propose Semantic-Consistent and Attention-based Networks (SCAN), which regularize the embeddings of the two modalities through aligning output semantic probabilities. We show that we can outperform several state-of-the-art cross-modal retrieval strategies for food images and cooking recipes by a significant margin.
  arXiv  Detail & Related papers  (2020-03-09T07:41:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.