Abstract
Precision agriculture (PA) and yield gap (Yg) analysis are promising strategies to achieve the desired sustainable intensification of agricultural production systems. Current crop Yg approaches do not consider the internal field yield variability caused by soil properties. Topographic and edaphic characteristics causing consistent high and low yield patterns in time and space can be interpreted as an ecological niche and used as proxies for potential yield (Yp) and Yg. Ecological niche models (ENMs) are statistical models originally developed to forecast a species' niche. However, its application to analyse crop yield spatio-temporal variability has never been made. This study aimed to fill this void by developing a novel approach: i) to quantify the magnitude and spatiotemporal distribution of Yp and Yg, ii) to identify the main factors that cause the Yg, and iii) to provide statistical and agronomical interpretation of the data to reduce the Yg. We performed this work using high-resolution maize yield maps from three seasons, with an ancillary dataset composed of soil electrical conductivity, soil properties and digital elevation models provided by Quinta da Cholda, Portugal. The yield maps were averaged, resulting in a standardised multiyear yield map. The 90th and 10th yield percentiles were interpreted as proxies for Yp and Yg, and analysed by an ENM machine learning algorithm - maximum entropy (MaxEnt). The average Yg and Yp were quantified as 1.5 and 19.1 ton/ha. Yp was characterised by having silty, richer soils and lower elevations, with several nutritional factors above the critical limits to maintain higher yields. Yg had loam soils coupled with higher relative elevations and lower nutrition content. This innovative modelling approach can efficiently manage high-dimensional spatio-temporal data to support advanced PA solutions, allowing detailed support for narrowing the Yg.

Abstract
This study used a tomography-like analysis to reconstruct the hyperspectral data from different tissues of the grapes: skin, pulp, and seeds. The dataset included 216 grapes of Loureiro (VIVC 25085) and 205 Vinhão (VIVC 13100) at various dates from the veraison until the harvest. A more comprehensive spectral data analysis identified how the internal tissues are related to the total grape spectra. Each tissue was reconstructed separately by decomposing the whole grapevine hyperspectral information. The results showed that the spectral reconstruction was more successful for Loureiro than Vinhão, with a mean absolute error of 6.08% and 33.32%, respectively. Partial least squares (PLS) regression models were developed for both cultivars using the reconstructed spectral data, enabling the modelling of ºBrix, puncture force (N), chlorophyll (a.u.), and anthocyanin content (a.u.). These models exhibited strong performance, with R2 > 0.8 and mean absolute percentage errors (MAPE) below 37%. This study emphasises the critical role of considering the grape's internal tissue in assessing its maturation process. The findings introduce an innovative methodology for efficiently evaluating grape maturation dynamics and inner tissue characteristics. By highlighting the importance of internal tissue analysis, this research paves the way for expedited and accurate monitoring of grape maturation, offering valuable insights into physiological-based viticultural practices and grape quality assessment. © The Authors, published by EDP Sciences. This is an open access article distributed under the terms of the Creative Commons Attribution License 4.0 (https://creativecommons.org/licenses/by/4.0/).

Abstract
Energy consumption has been increasing in the last years and thus, energy efficiency is one of the most important topics actually. Besides, the consumption and energy generation forecast help in efficiency optimization. This paper presents the development of a system for forecasting surplus power generation to be used by residential loads connected to smart plugs. In this way, it is intended to collaborate with the use of surplus energy production in electrical devices in a residence instead of sending to batteries or to the grid. This work presents the theoretical basis of the project and the architecture of the developed system. A Machine Learning method applied to photovoltaic generation data in a residence was used to predict surplus energy. © 2023 IEEE.

Abstract
Public lighting is crucial for maintaining the safety and well-being of communities. Current inspection methods involve examining the luminaires during the day, but this approach has drawbacks, including energy consumption, delay in detecting issues, and high costs and time investment. Utilising deep learning based automatic detection is an advanced method that can be used for identifying and locating issues in this field. This study aims to use deep learning to automatically detect burnt-out street lights, using Seville (Spain) as a case study. The study uses high-resolution night time imagery from the JL1-3B satellite to create a dataset called NLight, which is then divided into three subsets: NL1, NL2, and NT. The NL1 and NL2 datasets are used to train and evaluate YOLOv5 and YOLOv7 segmentation models for instance segmentation of streets. And then, distance outliers were detected to find the lights off. Finally, the NT dataset is used to evaluate the effectiveness of the proposed methodology. The study finds that YOLOv5 achieved a mask mAP of 57.7%, and the proposed methodology had a precision of 30.8% and a recall of 28.3%. The main goal of this work is accomplished, but there is still space for future work to improve the methodology.

Abstract
Public lighting plays a very important role for society's safety and quality of life. The identification of faults in public lighting is essential for the maintenance and prevention of safety. Traditionally, this task depends on human action, through checking during the day, representing expenditure and waste of energy. Automatic detection with deep learning is an innovative solution that can be explored for locating and identifying of this kind of problem. In this study, we present a first approach, composed of several steps, intending to obtain the segmentation of public lighting, using Seville (Spain) as case study. A dataset called NLight was created from a nighttime image taken by the JL1-3B satellite, and four U-Net and FPN architectures were trained with different backbones to segment part of the NLight. The U-Net with InceptionResNetv2 proved to be the model with the best performance, obtained 761 of 815, correct locations (93.4%). This model was used to predict the segmentation of the remaining dataset. This study provides the location of lamps so that we can identify patterns and possible lighting failures in the future.

Abstract
The grape moth is a common pest that affects grapevines by consuming both fruit and foliage, rendering grapes deformed and unsellable. Integrated pest management for the grape moth heavily relies on pheromone traps, which serve a crucial function by identifying and tracking adult moth populations. This information is then used to determine the most appropriate time and method for implementing other control techniques. This study aims to find the best method for detecting small insects. We evaluate the following recent YOLO models: v5, v6, v7, and v8 for detecting and counting grape moths in insect traps. The best performance was achieved by YOLOv8, with an average precision of 92.4% and a counting error of 8.1%.