Supporting Scientific Research Through Machine and Deep Learning: Fluorescence Microscopy and Operational Intelligence Use Cases

Although the debate of what data science is has a long history and has not reached a complete consensus yet, Data Science can be summarized as the process of learning from data. Guided by the above vision, this thesis presents two independent data science projects developed in the scope of multidisciplinary applied research. The first part analyzes fluorescence microscopy images typically produced in life science experiments, where the objective is to count how many marked neuronal cells are present in each image. Aiming to automate the task for supporting research in the area, we propose a neural network architecture tuned specifically for this use case, cell ResUnet (c-ResUnet), and discuss the impact of alternative training strategies in overcoming particular challenges of our data. The approach provides good results in terms of both detection and counting, showing performance comparable to the interpretation of human operators. As a meaningful addition, we release the pre-trained model and the Fluorescent Neuronal Cells dataset collecting pixel-level annotations of where neuronal cells are located. In this way, we hope to help future research in the area and foster innovative methodologies for tackling similar problems. The second part deals with the problem of distributed data management in the context of LHC experiments, with a focus on supporting ATLAS operations concerning data transfer failures. In particular, we analyze error messages produced by failed transfers and propose a Machine Learning pipeline that leverages the word2vec language model and K-means clustering. This provides groups of similar errors that are presented to human operators as suggestions of potential issues to investigate. The approach is demonstrated on one full day of data, showing promising ability in understanding the message content and providing meaningful groupings, in line with previously reported incidents by human operators.

Collective actions for environmental monitoring and conservation: citizen science, informal environmental education, and participatory approach

This PhD was driven by an interest for inclusive and participatory approaches. The methodology that bridges science and society is known as 'citizen science' and is experiencing a huge upsurge worldwide, in the scientific and humanities fields. In this thesis, I have focused on three topics: i) assessing the reliability of data collected by volunteers; ii) evaluating the impact of environmental education activities in tourist facilities; and iii) monitoring marine biodiversity through citizen science. In addition to these topics, during my research stay abroad, I developed a questionnaire to investigate people's perceptions of natural areas to promote the implementation of co-management. The results showed that volunteers are not only able to collect sufficiently reliable data, but that during their participation in this type of project, they can also increase their knowledge of marine biology and ecology and their awareness of the impact of human behaviour on the environment. The short-term analysis has shown that volunteers are able to retain what they have learned. In the long term, knowledge is usually forgotten, but awareness is retained. Increased awareness could lead to a change in behaviour and in this case a more environmentally friendly attitude. This aspect could be of interest for the development of environmental education projects in tourism facilities to reduce the impact of tourism on the environment while adding a valuable service to the tourism offer. We also found that nature experiences in childhood are important to connect to nature in adulthood. The results also suggest that membership or volunteering in an environmental education association could be a predictor of people's interest in more participatory approaches to nature management. In most cases, the COVID -19 pandemic had not changed participants' perceptions of the natural environment.