Paolo Dell'Aversana

Dr. Paolo Dell'Aversana

orcid

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 April 2023 in Minerals
Verified
Journal Article
Open access
PDF file
Paolo Dell'AversanaPaolo Dell'Aversana
Paolo Dell'Aversana
Recent studies have demonstrated the potential of machine learning methods for fast and accurate mineral classification based on microscope thin sections. Such methods can be extremely useful to support geoscientists during the phases of operational geology, especially when mineralogical and petrological data are fully integrated with other geological and geophysical information. In order to be effective, these methods require robust machine learning models trained on pre-labeled data. Furthermore, it is mandatory to optimize the hyper-parameters of the machine learning techniques in order to guarantee optimal classification accuracy and reliability. Nowadays, deep learning algorithms are widely applied for image analysis and automatic classification in a large range of Earth disciplines, including mineralogy, petrography, paleontology, well-log analysis, geophysical imaging, and so forth. The main reason for the recognized effectiveness of deep learning algorithms for image analysis is that they are able to quickly learn complex representations of images and patterns within them. Differently from traditional image-processing techniques based on handcrafted features, deep learning models automatically learn and extract features from the data, capturing, in almost real-time, complex relationships and patterns that are difficult to manually define. Many different types of deep learning models can be used for image analysis and classification, including fully connected deep neural networks (FCNNs), convolutional neural networks (CNNs or ConvNet), and residual networks (ResNets). In this paper, we compare some of these techniques and verify their effectiveness on the same dataset of mineralogical thin sections. We show that the different deep learning methods are all effective techniques in recognizing and classifying mineral images directly in the field, with ResNets outperforming the other techniques in terms of accuracy and precision. In addition, we compare the performance of deep learning techniques with different machine learning algorithms, including random forest, naive Bayes, adaptive boosting, support vector machine, and decision tree. Using quantitative performance indexes as well as confusion matrixes, we demonstrate that deep neural networks show generally better classification performances than the other approaches. Furthermore, we briefly discuss how to expand the same workflow to other types of images and geo-data, showing how this deep learning approach can be generalized to a multiscale/multipurpose methodology addressed to the analysis and automatic classification of multidisciplinary information. This article has tutorial purposes, too. For that reason, we will explain, with a didactical level of detail, all the key steps of the workflow.

1 January 2022 in AIMS Geosciences
Verified
Journal Article
Open access
PDF file
Paolo Dell'AversanaPaolo Dell'Aversana
Paolo Dell'Aversana
In this paper, we introduce a novel inversion methodology that combines the benefits offered by Reinforcement-Learning techniques with the advantages of the Epsilon-Greedy method for an expanded exploration of the model space. Among the various Reinforcement Learning approaches, we applied the set of algorithms included in the category of the Q-Learning methods. We show that the Temporal Difference algorithm offers an effective iterative approach that allows finding an optimal solution in geophysical inverse problems. Furthermore, the Epsilon-Greedy method properly coupled with the Reinforcement Learning workflow, allows expanding the exploration of the model-space, minimizing the misfit between observed and predicted responses and limiting the problem of local minima of the cost function. In order to prove the feasibility of our methodology, we tested it using synthetic geo-electric data and a seismic refraction data set available in the public domain.

28 February 2024 in Minerals
Verified
Journal Article
Open access
PDF file
Paolo Dell'AversanaPaolo Dell'Aversana
Paolo Dell'Aversana
In this paper, we discuss the implementation of artificial self-awareness mechanisms and self-reflection abilities in deep neural networks. While the current limitations of research prevent achieving cognitive capabilities on par with natural biological entities, the incorporation of basic self-awareness and self-reflection mechanisms in deep learning architectures offers substantial advantages in tackling specific problems across various scientific fields, including geosciences. In the first section, we outline the foundational architecture of our deep learning approach termed Self-Aware Learning (SAL). The subsequent part of the paper highlights the practical benefits of this machine learning methodology through synthetic tests and applications addressed to automatic classification and image analysis of real petrological data sets. We show how Self-Aware Learning allows enhanced accuracy, reduced overfitting problems, and improved performances compared to other existing methods.

22 June 2016 in Geophysical Prospecting
Verified
Journal Article
Closed access
PDF file
Paolo Dell'AversanaPaolo Dell'Aversana
Paolo Dell'Aversana
GGGianluca Gabbriellini
Gianluca Gabbriellini
AAAlfonso Amendola
Alfonso Amendola

1 January 2024 in AIMS Geosciences
Verified
Journal Article
Open access
PDF file
Paolo Dell'AversanaPaolo Dell'Aversana
Paolo Dell'Aversana
Artificial general intelligence (AGI), or strong AI, aims to replicate human-like cognitive abilities across diverse tasks and domains, demonstrating adaptability and learning like human intelligence. In contrast, weak AI refers to systems designed for specific tasks, lacking the broad cognitive flexibility of AGI. This paper introduces a novel approach to optimize oil production by integrating fundamental principles of AGI with geophysical data inversion and continuous monitoring techniques. Specifically, the study explored how AGI-inspired algorithms, combined with established reinforcement learning (RL) techniques, can enhance borehole electric/electromagnetic monitoring and reservoir fluid mapping technology. This integration aims to mitigate the risk of unwanted water invasion in production wells while optimizing oil extraction. The proposed methodology leverages real-time geophysical data analysis and automated regulation of oil production. The paper begins by outlining the key features of AGI and RL, and then discusses their application in electric/electromagnetic monitoring to define optimal production policies. The effectiveness of this approach was verified through synthetic tests, showing significant improvements in production efficiency, resource recovery, and environmental impact reduction.

28 March 2025 in Minerals
Verified
Journal Article
Open access
PDF file
Paolo Dell'AversanaPaolo Dell'Aversana
Paolo Dell'Aversana
MycelialNet is a novel deep neural network (DNN) architecture inspired by natural mycelial networks. Mycelia, the vegetative part of fungi, form extensive underground networks that, in a very efficient way, connect biological entities, transport nutrients and signals, and dynamically adapt to environmental conditions. Drawing inspiration from these properties, MycelialNet integrates dynamic connectivity, self-optimization, and resilience into its artificial structure. This paper explores how mycelial-inspired neural networks can enhance big data analysis, particularly in mineralogy, petrology, and other Earth disciplines, where exploration and exploitation must be efficiently balanced during the process of data mining. We validate our approach by applying MycelialNet to synthetic data first, and then to a large petrological database of volcanic rock samples, demonstrating its superior feature extraction, clustering, and classification capabilities with respect to other conventional machine learning methods.