Environmental problems such as air pollution monitoring and prevention, flood detection and prevention, land use, forest management, river water quality, wastewater treatment supervision, management of biodiversity etc. are more complex than typical realworld problems usually AI faces to.This added complexity rises from several aspects, such as the randomness shown by most of environmental processes involved, the 2D/3D nature of involved problems, the temporal aspects, the spatial aspects, the inexactness of the information, the multigranularity of the information etc.In fact, environmental problems belong to the most difficult problems with a lot of inexactness and uncertainty, and possibly conflicting objectives to be solved according to several classifications such as the one by Funtowicz Ravetz (Funtowicz Ravetz, 1999), which states that there are 3 kinds of problems.Also, they are non-structured problems in the classification proposed by H. Simon (Simon, 1966).All this complexity means that to effectively solve those problems a lot of knowledge is needed.This knowledge can be theoretical knowledge expressed in mechanistic models, such as the Gravidity Newton's Theory, or it can be empirical knowledge that can be expressed by means of empirical models, originated by some data and observations (data-driven knowledge) or by the expertise gathered by people when coping with such problems (model-driven knowledge, particularly expert-based knowledge).The KDD 2024 Special Day for AI for environment brings together researchers and practitioners to present their perspective on this very timely topic on how AI can be used for good, and improving the environment where we all live in.

One of the major problems when designing control and supervision systems for environmental systems is the need to be adapted to the particularities of each system. The use of Artificial Intelligence (AI) techniques instead of classical control approaches have been used in recent years in the design of Intelligent Decision Support Systems (IDSS). A static Case-Based Reasoning (CBR) approach for the control and supervision of environmental systems has been proposed in previous works, providing a general efficient methodology to allow scalability to further types of systems. However, the dynamic nature of environmental processes suggests temporary dependencies between cases, hence the use of a temporal CBR (TCBR) approach could provide better performance. The main contribution of this research is to propose a new TCBR method providing improved retrieval process, leading to improved overall performance by considering the dependency of consecutive cases. Thus, the retrieval process is addressed considering not only a single case but a set of consecutive cases named episodes. Our proposal is based on using fixed-length episodes. The approach presented has been tested in a real facility within the ambit of a local water administration in the area of Barcelona. The results indicated that the TCBR approach improved the accuracy of the obtained solutions and case diagnosis with respect to the single-case CBR approach. A tuning process with different episode lengths is performed in order to find a good trade-off between performance and computing time.

Bacterial resistance to antibiotics has been rapidly increasing, resulting in low antibiotic effectiveness even treating common infections. The presence of resistant pathogens in environments such as a hospital Intensive Care Unit (ICU) exacerbates the critical admission-acquired infections. This work focuses on the prediction of antibiotic resistance in Pseudomonas aeruginosa nosocomial infections at the ICU, using Long Short-Term Memory (LSTM) artificial neural networks as the predictive method. The analyzed data were extracted from the Electronic Health Records (EHR) of patients admitted to the University Hospital of Fuenlabrada from 2004 to 2019 and were modeled as Multivariate Time Series. A data-driven dimensionality reduction method is built by adapting three feature importance techniques from the literature to the considered data and proposing an algorithm for selecting the most appropriate number of features. This is done using LSTM sequential capabilities so that the temporal aspect of features is taken into account. Furthermore, an ensemble of LSTMs is used to reduce the variance in performance. Our results indicate that the patient's admission information, the antibiotics administered during the ICU stay, and the previous antimicrobial resistance are the most important risk factors. Compared to other conventional dimensionality reduction schemes, our approach is able to improve performance while reducing the number of features for most of the experiments. In essence, the proposed framework achieve, in a computationally cost-efficient manner, promising results for supporting decisions in this clinical task, characterized by high dimensionality, data scarcity, and concept drift.

In this paper, we investigate Astronomical Observations Scheduling which is a type of Multi-Objective Combinatorial Optimization Problem, and detail its specific challenges and requirements and propose the Hybrid Accumulative Planner (HAP), a hybrid multi-start metaheuristic scheduler able to adapt to the different variations and demands of the problem. To illustrate the capabilities of the proposal in a real-world scenario, HAP is tested on the Atmospheric Remote-sensing Infrared Exoplanet Large-survey (Ariel) mission of the European Space Agency (ESA), and compared with other studies on this subject including an Evolutionary Algorithm (EA) approach. The results show that the proposal outperforms the other methods in the evaluation and achieves better scientific goals than its peers. The consistency of HAP in obtaining better results on the available datasets for Ariel, with various sizes and constraints, demonstrates its competence in scalability and adaptability to different conditions of the problem.

AI is one of the biggest megatrends towards the 4th industrial revolution. Although these technologies promise business sustainability as well as product and process quality, it seems that the ever-changing market demands, the complexity of technologies and fair concerns about privacy, impede broad application and reuse of Artificial Intelligence (AI) models across the industry. To break the entry barriers for these technologies and unleash its full potential, the knowlEdge project will develop a new generation of AI methods, systems, and data management infrastructure. Subsequently, as part of the knowlEdge project we propose several major innovations in the areas of data management, data analytics and knowledge management including (i) a set of AI services that allows the usage of edge deployments as computational and live data infrastructure as well as a continuous learning execution pipeline on the edge, (ii) a digital twin of the shop-floor able to test AI models, (iii) a data management framework deployed along the edge-to-cloud continuum ensuring data quality, privacy and confidentiality, (iv) Human-AI Collaboration and Domain Knowledge Fusion tools for domain experts to inject their experience into the system, (v) a set of standardisation mechanisms for the exchange of trained AI models from one context to another, and (vi) a knowledge marketplace platform to distribute and interchange trained AI models. In this paper, we present a short overview of the EU Project knowlEdge –Towards Artificial Intelligence powered manufacturing services, processes, and products in an edge-to-cloud-knowledge continuum for humans [in-the-loop], which is funded by the Horizon 2020 (H2020) Framework Programme of the European Commission under Grant Agreement 957331. Our overview includes a description of the project’s main concept and methodology as well as the envisioned innovations.

Although widely used, the majority of current music recommender systems still focus on recommendations' accuracy, user preferences and isolated item characteristics, without evaluating other important factors, like the joint item selections and the recommendation moment. However, when it comes to playlist recommendations, additional dimensions, as well as the notion of user experience and perception, should be taken into account to improve recommendations' quality. In this work, HybA, a hybrid recommender system for automatic playlist continuation, that combines Latent Dirichlet Allocation and Case-Based Reasoning, is proposed. This system aims to address “similar concepts” rather than similar users. More than generating a playlist based on user requirements, like automatic playlist generation methods, HybA identifies the semantic characteristics of a started playlist and reuses the most similar past ones, to recommend relevant playlist continuations. In addition, support to beyond accuracy dimensions, like increased coherence or diverse items' discovery, is provided. To overcome the semantic gap between music descriptions and user preferences, identify playlist structures and capture songs' similarity, a graph model is used. Experiments on real datasets have shown that the proposed algorithm is able to outperform other state of the art techniques, in terms of accuracy, while balancing between diversity and coherence.

Recommender Systems have recently become a fundamental part of various applications intending to support the users when searching for information, products and services that could be interested in at a given moment. While the majority of the current Recommender Systems generate Isolate item recommendations based on user-item interactions, mainly expressed through ratings, this paper presents a system generating recommendations of sets of items. The objective of this system is to generate accurate recommendations in domains where users are looking for a more complete experience, in terms of joint item selections, and where the complexity of the related information cannot be evaluated and treated efficiently using the actual systems, like in the music playlist recommendations. In order to identify the underlying relations between songs, their styles and the artists that perform those, a hybrid Case-Based Reasoning approach combined with a graph model is used. This framework was designed with the scope to overcome the semantic gap present in multimedia recommendations, and at the same time, to be able to perform better in cold start situations. The experimentation results presented, show that the proposed approach is able to deliver recommendations of equal and higher accuracy than some of the widely used recommendation methods.

Classical pre-post intervention studies are often analyzed using traditional statistics. Nevertheless, the nutritional interventions have small effects on the metabolism and traditional statistics are not enough to detect these subtle nutrient effects. Generally, this kind of studies assumes that the participants are adhered to the assigned dietary intervention and directly analyzes its effects over the target parameters. Thus, the evaluation of adherence is generally omitted. Although, sometimes, participants do not effectively adhere to the assigned dietary guidelines. For this reason, the trajectory map is proposed as a visual tool where dietary patterns of individuals can be followed during the intervention and can also be related with nutritional prescriptions. The trajectory analysis is also proposed allowing both analysis: 1) adherence to the intervention and 2) intervention effects. The analysis is made by projecting the differences of the target parameters over the resulting trajectories between states of different time-stamps which might be considered either individually or by groups. The proposal has been applied over a real nutritional study showing that some individuals adhere better than others and some individuals of the control group modify their habits during the intervention. In addition, the intervention effects are different depending on the type of individuals, even some subgroups have opposite response to the same intervention.