uncertainty. Weekly equipment sensor and blasthole data updated the stochastic scenarios over time to improve performance. In both cases, fixed processing conditions are assumed with fixed recovery rates. While the methods proposed by Levinson et al. (2023) and Kumar et al. (2021) provide policies that are potentially robust to geological uncertainty, they focus on mine planning rather than material handling and downstream processing. As a consequence, these methods do not incorporate process variability beyond upstream stages such as preconcentration and mining equipment, and are aimed at developing production schedules over weeks or months, rather than days or even hours. The work by Azzamouri shows that blending decisions are made on a day-today basis (in practice, even an hour-to-hour basis) which reflects the fact that ore and process variability do not just occur over week to month long periods but can shift dramatically by day or hour. To bridge the gap between the tactical logistics models of Azzamouri and the adaptive mining agents of Kumar and Levinson, we take the first step in applying the POMDP approach proposed by Xu et al. (2025) to the Moroccan phosphate context. This framework incorporates both feedstock and process variability to optimize mineral processing operations in real-time and is well-equipped to address the problem of feedstock blending and routing under uncertainty. 2. OBJECTIVES This work explores an adaptive, data-driven approach to mineral blending and routing under uncertainty using reinforcement learning. We aim to show that: 1. Feedstock blending and routing can be formulated as a problem of decision-making under uncertainty, incorporating both ore and process variability. 2. State-of-the-art deterministic approaches like linear programming inherently fail to account for the uncertainties that arise from ore and process variability, which limits performance. 3. By formulating feedstock blending and routing as a Markov Decision Process (MDP), approaches like Monte Carlo Tree Search (MCTS), which directly account for uncertainty in decision-making, can be employed to improve product consistency and ultimately increase net present value (NPV). 4. This formulation is adaptable to most feedstock blending scenarios, and serves as the foundation for future real-world case studies and eventual extension to a Partially Observable MDP (POMDP) framework incorporating uncertainty reduction. 3. METHODOLOGY 3.1 Blending Network Model The problem of feedstock blending and routing is modeled as a layered directed acyclic graph (also known as a feedforward network), where nodes represent sources or destinations of material and edges represent flows of material. The four layers in the network represent mines, piles, process pathways, and clients respectively. Flow assignments are made each day. A simple
RkJQdWJsaXNoZXIy MTM0Mzk2