With the aim of estimating the growth of tomatoes during the agricultural season, we propose to segment tomatoes in images acquired in open field, and to derive their size from the segmentation results obtained in pairs of images acquired each day. To cope with difficult conditions such as occlusion, poor contrast and movement of tomatoes and leaves, we propose to base the segmentation of an image on the result obtained on the image of the previous day, guaranteeing temporal consistency, and to incorporate a shape constraint in the segmentation procedure, assuming that the image of a tomato is approximately an ellipse, guaranteeing spatial consistency. This is achieved with a parametric deformable model with shape constraint. Results obtained over three agricultural seasons are very good for images with limited occlusion, with an average relative distance between the automatic and manual segmentations of 6.46 % (expressed as percentage of the size of tomato).

To fulfil the increasing need for food of the growing population and face climate change, modern technologies have been applied to improve different farming processes. One important application scenario is to detect and measure natural hazards using sensors and data analysis techniques. Crowdsensing is a sensing paradigm that empowers ordinary people to contribute with data their sensor-enhanced mobile devices gather or generate. In this paper, we propose to use Twitter as an open crowdsensing platform for acquiring farmers knowledge. We proved this concept by applying pre-trained language models to detect individual's observation from tweets for pest monitoring.

Data mining in social media has been widely applied in different domains for monitoring and measuring social phenomena, such as opinion analysis towards popular events, sentiment analysis of a population, detecting early side effects of drugs, and earthquake detection. Social media attracts people to share information in open environments. Facing the newly forming technical lock-ins and the loss of local knowledge in agriculture in the era of digital transformation, the urge to reestablish a farmer-centric precision agriculture is urgent. The question is whether social media like Twitter can help farmers to share their observations towards the constitution of agricultural knowledge and monitoring tools. In this work, we develop several scenarios to collect tweets, then we applied different natural language processing techniques to measure their informativeness as a source for phytosanitary monitoring.

Agriculture is one of the areas whose activities depend heavily on weather forecasts. Indeed, in order to optimize their production, farmers must be able to anticipate climate conditions favorable or not to their activities by deploying the appropriate action plans. For this purpose, they consult the data daily from various suppliers of weather forecasts. However, the reliability of the forecasts of each supplier is variable according to the period, the climate or the geographical area. Farmers, therefore, have to arbitrate between suppliers daily. This paper proposes a new set of learning architecture that significantly improves the accuracy of weather short-term forecasts for the next 1-12h in order to assist farmers in decision-making.