Engineered nanomaterials (NMs) have unique physicochemical features whose potential is being explored in precision and sustainable agriculture for instance, as nano-fertilizers to improve crop yield and nutritional quality1. Agrochemicals used to protect crops against pathogens can be substituted by nano-pesticides which can target pests more effectively with fewer pesticides, minimizing widespread effects on soil health and biodiversity while also increasing soil function and nutrient cycling by boosting the soil microbiota [1]. Plant resilience to extreme environmental conditions can be also enhanced through nano-biotechnology applications giving plants improved functionalities that will help them cope with environmental stress due to climate change [1,2]. Future nano-agriculture uses include the creation of smart plant sensors, in which the plant itself is tuned to monitor soil/water quality and detect biotic/abiotic stresses, and translate the plant chemical signal into a digital signal that can then be utilised to control NM delivery to the system. While the focus here is on plant systems, it is notable also that nanomaterials are also beginning to be applied to livestock farming, including optimisation of nutrient delivery, as biocidal agents, and as tools in veterinary medicine and reproduction. Computational modelling or nanoinformatics (defined as the application of computer algorithms to the analysis of data to identify patterns not visible to the human eye, or to calculate properties from first principles based on fundamental laws of physics) can provide critical insights in for optimisation of agricultural productivity. Key to all nanoinformatics approaches is the need for a deep understanding of the fundamental mechanisms of interactions of the nanomaterials with the plant-soil and plant-animal systems, and how these interactions change as a function of the nanomaterials properties, the environmental conditions (e.g., soil properties, climate and weather conditions) and the nature of the crops or livestock systems under consideration. For instance, nitrogen use efficiency and optimization of nanoforms of key micro and macronutrients, the reduction of air and water pollution arising from overuse of nitrogen and phosphorus-based fertilizers are key elements in improving the sustainability of agricultural production. Therefore, with the combination of experimental data from various soil conditions, plant species, climate conditions, and NMs physicochemical properties, Machine Learning approaches may be able to predict both the impacts of NMs on the agricultural system (on plants and soil) and vice versa -the effects of the agricultural system to the NMs (transformations, distribution, and bioavailability). This will contribute to the development of nano-agrochemicals that are safer-by-design and combine both optimized safety and enhanced functionalities [1]. Here we demonstrate the potential for translation of existing nanosafety modelling approaches to support the development of precision agriculture and contribute to achievement of the UN Sustainable Development Goal of food for all in an increasingly climate stressed world. 1. P. Zhang, Z. Guo, S. Ullah, G. Melagraki, A. Afantitis and I. Lynch, Nanotechnology and artificial intelligence to enable sustainable and precision agriculture. Nat. Plants, 2021, 7, 864–876. https://doi.org/10.1038/s41477-021-00946-6 2. G. Revathy, P. Aurchana, R. Madonna Arieth, N. S. Kavitha, A. Ramalingam, and Kiran Ramaswamy. HANA: A Performance-Based Machine Learning and Neural Network Approach for Climate Resilient Agriculture. Journal of Nanoparticles, 2022 |Article ID 2658211. https://doi.org/10.1155/2022/2658211