The elimination of hunger, food insecurity and malnutrition with the aim of creating the basis for a world whose inhabitants feed themselves sufficiently and in a healthy way, in line with their nutritional needs and their food preferences. These are the goals of FAO (Food and Agriculture Organization) for 2030. All researchers are called to make their important contribution.Today there are 842 million hungry people, of whom 200 million are children. From the other European Food Safety Authority (EFSA) declares that 88 million tons of food are thrown away every year, or 173 Kg per person. Data that FAO reports worldwide, 45% of the food produced is thrown away. How nanotechnology can help and contribute to the reduction of food waste, valuable waste if reusable[1]. Nanotechnologies can support the whole process from farm to fork, ensuring that less food is wasted and therefore better used, without compromising the health of the consumer.In this work several studies will be presented in which, Small Sensor System (S3), based on gas sensors with nanomaterials has been used to identify possible contamination of foodstuff and reduce food waste.All the analyzed samples, were prepared in an identical manner for all the techniques used in parallel so as to minimize possible differences. In general, in the food field, techniques that do not go to destroy the sample are preferred, that are fast, and user-friendly, so as to be able to combine as much as possible the real production and food processing.The S3 (Fig.1), consists of a pneumatic part, an electronic part and a chamber with a maximum 10 MOX gas sensors, and an online data acquisition and processing app. Flow, temperature, humidity sensors, and actuators (valves and pumps) are all embedded inside the S3 device. Techniques have been used in parallel to train the sensors, are chemical (GC-MS with SPME) and microbiological (growth media), depending on the specific objective of the application and the nature of the samples [2]. In the case of the reduction of possible microbiological contaminations, the samples will be prepared with known concentrations of bacteria, yeasts or molds, to reproduce real samples.Once acquired and transmitted, data must be analyzed to extract relevant information. Machine learning algorithms are widely used to achieve this purpose, ranging from unsupervised methods (as PCA) to supervised learning (like neural networks, k-NN, SVM, random forest as few examples).Remarkable results have been obtained that demonstrate how the S3 device is able to discriminate in a surprising manner the samples analyzed. The reported results in the food sector concern different types of high applicative interest:- Identification of possible microbiological contaminants such as that from Campylobacter jejuni (Fig.2)[3], - Geographical identification of raw materials (Fig. 3)[4],- Evolution of the shelf-life of a product during the preparation or storage phases,- Environmental monitoring (Fig. 4), such as water purification, air pollution.The food matrices are all complex and constantly evolving, and a device like S3 turns out to bring a considerable advantage to the online control. An advantage that makes it possible to reduce the loss of products at any time, and at the same time increases control enlarging the number of samples analyzed and reducing costs. The aforementioned results demonstrate how nanotechnology and in particular S3 device can contribute to reach the “zero hunger” goal all over the world.[1] S. Vermani, Farm to Fork: IOT for Food Supply Chain, International Journal of Innovative Technology and Exploring Engineering (IJITEE), 8 (2019) 4915 - 4919. DOI: 10.35940/ijitee.L3551.1081219.[2] A.Abbatangelo, E. Núñez-Carmona, V. Sberveglieri, Application of a novel S3 nanowire gas sensor device in parallel with GC-MS for the identification of Parmigiano Reggiano from US and European competitors, J. Food Eng. 236 (2018) 36–43.doi:10.3390/s18051617.[3] E. Núñez-Carmona, M. Abbatangelo,, V. Sberveglieri, Innovative Sensor Approach to Follow Campylobacter jejuni Development, Biosensors, 9 (1) (2019) Article number bios9010008 DOI: 10.3390/bios9010008[4] M. Abbatangelo, E. Núñez-Carmona, G. Duina, V. Sberveglieri, V., Multidisciplinary approach to characterizing the fingerprint of Italian EVoO, Molecules, 24 (8) (2019), DOI: 10.3390/molecules24081457. Figure 1