Abstract
The Atacama desert is a region with exceptional conditions for solar power production. However, despite its relevance, the impact of climate change on this resource in this region has barely been studied. Here, we use regional climate models to explore how climate change will affect the photovoltaic solar power resource per square meter (PVres) in Atacama. Models project average reductions in PVres of 1.5% and 1.7% under an RCP8.5 scenario, respectively, for 2021-2040 and 2041-2060. Under RCP2.6 and the same periods, reductions range between 1.2% and 0.5%. Also, we study the contribution to future changes in PVres of the downwelling shortwave radiation, air temperature and wind velocity. We find that the contribution from changes in wind velocity is negligible. Future changes of downwelling shortwave radiation, under the RCP8.5 scenario, cause up to 87% of the decrease of PVres for 2021-2040 and 84% for 2041-2060. Rising temperatures due to climate change are responsible for drops in PVres ranging between 13%–19% under RCP2.6 and 14%–16% under RCP8.5. We conclude that climate change has the potential to impact the PVres in the Atacama region while retaining exceptional conditions for solar power production.

Abstract
Plant diseases and pests significantly influence food production and the productivity and economic profitability of agricultural crops. This has led to great interest in developing technological solutions to enable timely and accurate detection. This systematic review aimed to find studies on the automation of processes to detect, identify and classify diseases and pests in agricultural crops. The goal is to characterize the class of algorithms, models and their characteristics and understand the efficiency of the various approaches and their applicability. The literature search was conducted in two citation databases. The initial search returned 278 studies and, after removing duplicates and applying the inclusion and exclusion criteria, 48 articles were included in the review. As a result, seven research questions were answered that allowed a characterization of the most studied crops, diseases and pests, the datasets used, the algorithms, their inputs and the levels of accuracy that have been achieved in automatic identification and classification of diseases and pests. Some trends that have been most noticed are also highlighted.

Abstract
Morphing attacks keep threatening biometric systems, especially face recognition systems. Over time they have become simpler to perform and more realistic, as such, the usage of deep learning systems to detect these attacks has grown. At the same time, there is a constant concern regarding the lack of interpretability of deep learning models. Balancing performance and interpretability has been a difficult task for scientists. However, by leveraging domain information and proving some constraints, we have been able to develop IDistill, an interpretable method with state-of-the-art performance that provides information on both the identity separation on morph samples and their contribution to the final prediction. The domain information is learnt by an autoencoder and distilled to a classifier system in order to teach it to separate identity information. When compared to other methods in the literature it outperforms them in three out of five databases and is competitive in the remaining.

Abstract
This study investigated the crucial factors for measuring the success of the information system used in the e-learning process, considering the transformations in the work environment. This study was motivated by the changes caused by COVID-19 witnessed after the shift to fully online learning environments supported by e-learning systems, i.e., learning emphasized with information systems. Empirical research was conducted on a sample comprising teaching staff from two European universities: the University of Novi Sad, Faculty of Technical Sciences in Serbia and the Polytechnic Institute of Castelo Branco in Portugal. By synthesizing knowledge from review of the prior literature, supported by the findings of this study, the authors propose an Extended Information System Success Measurement Model-EISSMM. EISSMM underlines the importance of workforce agility, which includes the factors of proactivity, adaptability, and resistance to change, in the information system performance measurement model. The results of our research provide more extensive evidence and findings for scholars and practitioners that could support measuring information system success primarily in e-learning and other various contextual settings, highlighting the importance of people's responses to work environment changes.

Abstract
The refractometric analysis of ethanol-water mixtures is hampered because this type of binary solution does not present a linear behavior. In this letter, a multimode graded-index fiber (GIF) tip sensor for the measurement of ethanol in binary liquid solutions of ethanol-water is proposed. The proof is fabricated by the fusion-splicing of a 500 mu m GIF to a single-mode fiber (SMF), and it operates as a refractometric sensor in reflection. To evaluate the prove potential to detected ethanol variations, samples of ethanol-water mixtures were measured at different temperatures (20 degrees C-60 degrees C). The samples have different %(v/v) of ethanol, in a range between 0% and 100%.

Abstract
The study of data quality in crowdsourcing campaigns is currently a prominent research topic, given the diverse range of participants involved. A potential solution to enhancing data quality processes in crowdsourcing is cognitive personalization, which involves appropriately adapting or assigning tasks based on a crowd worker's cognitive profile. There are two common methods for assessing a crowd worker's cognitive profile: administering online cognitive tests, and inferring behavior from task fingerprinting based on user interaction log events. This article presents the findings of a study that investigated the complementarity of both approaches in a microtask scenario, focusing on personalizing task design. The study involved 134 unique crowd workers recruited from a crowdsourcing marketplace. The main objective was to examine how the administration of cognitive ability tests can be used to allocate crowd workers to microtasks with varying levels of difficulty, including the development of a deep learning model. Another goal was to investigate if task fingerprinting can be used to allocate crowd workers to different microtasks in a personalized manner. The results indicated that both objectives were accomplished, validating the usage of cognitive tests and task fingerprinting as effective mechanisms for microtask personalization, including the development of a deep learning model with 95% accuracy in predicting the accuracy of the microtasks. While we achieved an accuracy of 95%, it is important to note that the small dataset size may have limited the model's performance.