The ML4QD project aims to exploit the synergies and common interests of the two collaborating groups to rationalize and model carrier dynamics in semiconductor QDs. This project will use ultrafast spectroscopy data generated by the CSIC group as input, and then develop ad-hoc Machine Learning Force-Fields (MLFFs) to perform electron dynamics on QD model systems, aligning with the QD sizes and timescales used in the experiments. These modelling tools will be developed and applied under the supervision of Prof. Infante at BCMaterials. The proposal is particularly timely and advantageous because the QD solids prepared by the Multifunctional Optical Materials group are ligand-free, thus avoiding additional complexity in computational simulations. These QD solids also exhibit tunable carrier dynamics and transport properties through QD connectivity, allowing for a distinct comparative analysis of isolated and interconnected QDs. The ML4QD project aims to solve a longstanding problem in nanoscience: simulating carrier dynamics in QDs within the time range of femtoseconds to nanoseconds.