Explainable Machine Learning for Scientific Insights and Discoveries
Open accessThe DOI matches its Crossref record; 135 of the 137 references it cites were found in a registry or an index.
Abstract
Machine learning methods have been remarkably successful for a wide range of application areas in the extraction of essential information from data. An exciting and relatively recent development is the uptake of machine learning in the natural sciences, where the major goal is to obtain novel scientific insights and discoveries from observational or simulated data. A prerequisite for obtaining a scientific outcome is domain knowledge, which is needed to gain explainability, but also to enhance scientific consistency. In this article, we review explainable machine learning in view of applications in the natural sciences and discuss three core elements that we identified as relevant in this context: transparency, interpretability, and explainability. With respect to these core elements, we provide a survey of recent scientific works that incorporate machine learning and the way that explainable machine learning is used in combination with domain knowledge from the application areas.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Several powerful AI algorithms are employing a so-called “black box” approach, where it is difficult or even impossible to understand how the obtained results have been achieved.66”
From Addressing bias in big data and AI for health care: A call for open science (2021) · cites this paper as [66]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“image or a video. Lerer et al. [2016] and Li et al. [2016] use video simulations to learn intuitive physics, for example about the stability of wooden block towers. Lerer et al. [2016] use ResNet-34 [He et al., 2016] and Googlenet [Szegedy et al., 2015] to predict the fall of towers of wooden blocks, as well as DeepMa…”
MethodGradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 1×
“o clips containing 101 objects of dierent characteristics, which was built for the task of deriving physical parameters such as velocity and mass. In their work, they use the LeNet CNN architecture [LeCun et al., 1998] to capture visual as well as physical characteristics while explicitly integrating physical laws bas…”
MethodGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Gaussian Processes for Machine Learning
Rasmussen, C. E., & Williams, C. K. I. (2005) · doi:10.7551/mitpress/3206.001.0001 · Cited by 11,705
(2016) · Cited by 11,679
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
Adadi, A., & Berrada, M. (2018) · IEEE Access · doi:10.1109/access.2018.2870052 · Cited by 6,294 · cited 1×
“Further details, types of interpretation, and specific realization can be found in recent surveys [7], [8], [20].”
BackgroundDeep learning and process understanding for data-driven Earth system science
Reichstein, M., Camps-Valls, G., Stevens, B., Jung, M., Denzler, J., Carvalhais, N., & Prabhat (2019) · Nature · doi:10.1038/s41586-019-0912-1 · Cited by 5,673
Lipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427
Explanation in artificial intelligence: Insights from the social sciences
Miller, T. (2019) · Artificial Intelligence · doi:10.1016/j.artint.2018.07.007 · Cited by 5,302
Research works printed but not linked: 3
- 10.1037/0033-2909.110.3.499 · doi:10.1037/0033-2909.110.3.499 · Paper page
- frigg, 2018, Scientific representation, The Stanford Encyclopedia of Philosophy
- 10.1145/3233231 · doi:10.1145/3233231 · Paper page
Cited by
Items 301–400 of 999
Souza, M. C. O., Cruz, J. C., Rocha, B. A., Souza, J. M. O., Devóz, P. P., Santana, A. M., Campiglia, A. D., & Barbosa, F. (2023) · Chemosphere · doi:10.1016/j.chemosphere.2023.138975 · Cited by 20
Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces
Chormai, P., Herrmann, J., Müller, K., & Montavon, G. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3388275 · Cited by 58
“Explainable AI has been shown to be a promising approach to extract insights in the data and in the systems or processes that generates this data [2], [6].”
BackgroundCausal hybrid modeling with double machine learning—applications in carbon flux modeling
Cohrs, K.-H., Varando, G., Carvalhais, N., Reichstein, M., & Camps‐Valls, G. (2024) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ad5a60 · Cited by 40
“Explainable artificial intelligence (XAI) tackles questions on the explainability of black box models [26–28], which find growing usage in remote sensing problems [29, 30].”
Zhou, Y., Wang, K., Zhang, Y., Liang, D., & Li, J. (2024) · The Canadian Journal of Chemical Engineering · doi:10.1002/cjce.25562 · Cited by 24
Shan, R., Ning, H., Xu, Q., Su, X., Guo, M., & Jia, X. (2025) · Applied Sciences · doi:10.3390/app15168854 · Cited by 20
Gijón, A., Eiraudo, S., Manjavacas, A., Schiera, D. S., Molina-Solana, M., & Gómez‐Romero, J. (2025) · Computer Physics Communications · doi:10.1016/j.cpc.2025.109761 · Cited by 33
Explainable Machine Learning Methods for Classification of Brain States during Visual Perception
Islam, R., Andreev, A. V., Shusharina, N. N., & Hramov, A. E. (2022) · Mathematics · doi:10.3390/math10152819 · Cited by 19
(Explainable) Artificial Intelligence in Aerospace Safety-Critical Systems
Sutthithatip, S., Perinpanayagam, S., & Aslam, S. (2022) · IEEE Aerospace Conference (AERO) · doi:10.1109/aero53065.2022.9843612 · Cited by 21
Zhang, Y., Mao, J., Ricciuto, D. M., Jin, M., Yu, Y., Shi, X., Wullschleger, S. D., Tang, R., & Liu, J. (2023) · Science of Remote Sensing · doi:10.1016/j.srs.2023.100088 · Cited by 22
“The lack of interpretability makes ML-based fire attribution a challenging task (Jain et al., 2020; Roscher et al., 2020).”
BackgroundSokol, K., & Vogt, J. E. (2024) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3613905.3651047 · Cited by 35
“…to a distinction between scientific and algorithmic explanations determined by the scientific consistency of the explained predictive model, the lack of which may result in untruthful explanations that can be used to manipulate or persuade an explainee, or justify a preselected conclusion [8, 63].”
Explainable AI for Earth observation: current methods, open challenges, and opportunities
Taşkın, G., Aptoula, E., & Ertürk, A. (2024) · Elsevier eBooks · doi:10.1016/b978-0-44-319077-3.00012-2 · Cited by 24
Deep Learning-Based Real-Time Driver Cognitive Distraction Detection
Fresta, M., Bellotti, F., Bochenko, I., Lazzaroni, L., Merlhiot, G., Tango, F., & Berta, R. (2025) · IEEE Access · doi:10.1109/access.2025.3539392 · Cited by 27
Fite, S., Wahab, A., Paenurk, E., Gross, Z., & Gershoni‐Poranne, R. (2022) · Journal of Physical Organic Chemistry · doi:10.1002/poc.4458 · Cited by 17
Garzón, A., Kapelan, Z. S., Langeveld, J., & Taormina, R. (2022) · doi:10.1002/essoar.10509791.2 · Cited by 19
Unraveling the response of forests to drought with explainable artificial intelligence (XAI)
Vulova, S., Horn, K., Rocha, A. D., Brill, F., Somogyvári, M., Okujeni, A., Förster, M., & Kleinschmit, B. (2025) · Ecological Indicators · doi:10.1016/j.ecolind.2025.113308 · Cited by 21
Burggräf, P., Wagner, J., Heinbach, B., & Steinberg, F. (2021) · IEEE Access · doi:10.1109/access.2021.3075620 · Cited by 20
“mendation of the authors in [44] we included experts from the machine and plant manufacturer in this process.”
BackgroundMachine Learning in Embedded Systems: Limitations, Solutions and Future Challenges
Batzolis, E., Vrochidou, Ε., & Papakostas, G. A. (2023) · IEEE Annual Computing and Communication Workshop and Conference (CCWC) · doi:10.1109/ccwc57344.2023.10099348 · Cited by 24
“Machine learning is a subset of artificial intelligence that involves the use of algorithms to enable computers to learn from data and improve their performance on tasks without explicit programming [6].”
BackgroundLong, T., Wang, S., Cao, W., Zhou, H., Fernández, C., & Wang, Y. (2023) · Journal of Energy Storage · doi:10.1016/j.est.2023.107576 · Cited by 19
Barnard, A. S., & Fox, B. L. (2023) · Chemistry of Materials · doi:10.1021/acs.chemmater.3c00715 · Cited by 17
Bounded Confidence Revisited: What We Overlooked, Underestimated, and Got Wrong
Hegselmann, R. (2023) · Journal of Artificial Societies and Social Simulation · doi:10.18564/jasss.5257 · Cited by 22
Understanding the Decision of Machine Learning Based Intrusion Detection Systems
Dang, Q.-V. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-63924-2_22 · Cited by 20
Stomberg, T. T., Weber, I., Schmitt, M., & Roscher, R. (2021) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-v-3-2021-317-2021 · Cited by 21
“Besides the actual solving of the application task and the mere learning of relationships between observed data and the desired output, a recent but not yet widespread use of ML is the derivation of new scientific knowledge (Roscher et al., 2020a).”
BackgroundInfluentialSelf-citationConceptual Understanding through Efficient Automated Design of Quantum Optical Experiments
Krenn, M., Kottmann, J. S., Tischler, N., & Aspuru‐Guzik, A. (2021) · Refubium (Universitätsbibliothek der Freien Universität Berlin) · doi:10.17169/refubium-32186 · Cited by 17
Diefenbach, S., Christoforakos, L., Ullrich, D., & Butz, A. M. (2022) · Multimodal Technologies and Interaction · doi:10.3390/mti6100095 · Cited by 21
“Transparency is also one of the core elements of the currently booming field of explainable AI (see [9]).”
BackgroundBlack-box error diagnosis in Deep Neural Networks for computer vision: a survey of tools
Fraternali, P., Milani, F., Torres, R. N., & Zangrando, N. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-08100-9 · Cited by 18
“This perimeter excludes those contributions that address DNN behavior and performances but pursue different targets such as special-purpose and domain-dependent metrics, the visualization of DNN internal representations [24], model design for interpretability [4], and human-in-the-loop interpretation [27].”
BackgroundHuman-centric and semantics-based explainable event detection: a survey
Kolajo, T., & Daramola, O. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10525-0 · Cited by 23
“Roscher et al. ( 2020 ) made a clear distinction between interpretability, explainability, and transparency: Transparency takes into account the AI/machine learning strategy, interpret - ability considers the AI alongside the data, and explainability takes into account the model, the data, and…”
BackgroundMachine learning for small interfering RNAs: a concise review of recent developments
Lee, M. (2023) · Frontiers in Genetics · doi:10.3389/fgene.2023.1226336 · Cited by 20
“It is employed across a myriad of applications, ranging from recommendation systems (Batmaz et al., 2019) to autonomous driving Bachute and Subhedar (2021), and now, increasingly in life sciences (Roscher et al., 2020).”
BackgroundPredicting dynamic stability from static features in power grid models using machine learning
Titz, M., Kaiser, F. J., Kruse, J., & Witthaut, D. (2024) · Chaos An Interdisciplinary Journal of Nonlinear Science · doi:10.1063/5.0175372 · Cited by 23
Sauer, C. R., Burggräf, P., & Steinberg, F. (2024) · Production Engineering · doi:10.1007/s11740-024-01306-x · Cited by 40
“In this context, model-agnostic methods are particularly suited to the task at hand due to their flexibility concerning the ML algorithm used [32].”
A review on full-, zero-, and partial-knowledge based predictive models for industrial applications
Zampini, S., Parodi, G., Oneto, L., Coraddu, A., & Anguita, D. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.102996 · Cited by 25
de Abreu, E. C., & Florindo, J. B. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-77964-1_31 · Cited by 16
Identifiability and physical interpretability of hybrid, gray-box models - a case study
Hotvedt, M., Grimstad, B., & Imsland, L. (2021) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2021.08.273 · Cited by 17
Thompson, J. E., Nunn, S. L. E., Sarkar, S., & Clayton, B. (2023) · Veterinary Sciences · doi:10.3390/vetsci10020101 · Cited by 16
Ahmad, K., Maabreh, M., Ghaly, M., Khan, K., Qadir, J., & Al-Fuqaha, A. (2020) · arXiv.org · doi:10.48550/arxiv.2012.09110 · Cited by 20
“For instance, in [53, 54, 55, 56], a survey of existing literature on explainable AI is presented.”
BackgroundCNN-Based Rolling Bearing Fault Diagnosis Method With Quantifiable Interpretability
Jiang, K., Yang, Z., Jin, T., Chen, C., Liu, Z., & Zhang, B. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3551952 · Cited by 18
“Therefore, interpretable feature visualization is essential for enhancing users’ trust in the CNN model [8], [9], [10], [11].”
Daif, N., Nunno, F. D., Granata, F., Difi, S., Kişi, Ö., Heddam, S., Kim, S., Ikram, R. M. A., & Zounemat‐Kermani, M. (2025) · Stochastic Environmental Research and Risk Assessment · doi:10.1007/s00477-025-02984-4 · Cited by 17
“The selected evaluation criteria include the Mean Absolute Error (MAE), Root Mean Square Error (RMSE), management where model transparency is essential for informed decision-making (Reichstein et al. 2019 ; Roscher et al. 2020).”
Interpretable Machine Learning Reveals Dissimilarities Between Subtypes of Autism Spectrum Disorder
Garbulowski, M., Smolińska, K., Diamanti, K., Pan, G., Maqbool, K., Feuk, L., & Komorowski, J. (2021) · Frontiers in Genetics · doi:10.3389/fgene.2021.618277 · Cited by 15
“Machine learning can provide novel insights into medical and biological questions, but it is not a panacea (Rajkomar et al., 2019; Roscher et al., 2020).”
BackgroundOn the Development of a Wearable Animal Monitor
Fonseca, L., Corujo, D., Xavier, W., & Gonçalves, P. (2022) · Animals · doi:10.3390/ani13010120 · Cited by 15
“ML [23] is a branch of the field of Artificial Intelligence (AI), which seeks to use data and algorithms to imitate the way humans learn, gradually obtaining better results [24].”
BackgroundEducation 4.0: Explainable Machine Learning for Classification of Student Adaptability
Tiwari, R. G., Jain, A. K., Kukreja, V., & Ujjwal, N. (2022) · International Conference on Data Analytics for Business and Industry (ICDABI) · doi:10.1109/icdabi56818.2022.10041636 · Cited by 15
“Black box machine learning models, which are developed and learn directly from the data without human supervision or assistance, rely heavily on this idea[7]–[9].”
BackgroundYue, H., Wang, J., & Lu, M. (2023) · Crystal Growth & Design · doi:10.1021/acs.cgd.2c01441 · Cited by 17
Machine Un-learning: An Overview of Techniques, Applications, and Future Directions
Sai, S., Mittal, U., Chamola, V., Huang, K., Spinelli, I., Scardapane, S., Tan, Z., & Hussain, A. (2023) · Cognitive Computation · doi:10.1007/s12559-023-10219-3 · Cited by 32
“Another example would be expensive missions, like those of SpaceX, ISRO, NASA, etc., where a little mistake might cost millions or even billions of dollars [119, 120].”
Maitra, V., Arrasmith, C., & Shi, J. (2024) · Manufacturing Letters · doi:10.1016/j.mfglet.2024.09.138 · Cited by 23
Understanding Polymers Through Transfer Learning and Explainable AI
Miccio, L. A. (2024) · Applied Sciences · doi:10.3390/app142210413 · Cited by 16
Puri, V., Priyadarshini, I., Kataria, A., Rani, S., & Min, H. (2025) · IEEE Access · doi:10.1109/access.2025.3548645 · Cited by 22
“The concept of explainable ML encompasses critical aspects that prioritize the generation of outcomes comprehensible to users [40], [41].”
Gangwal, A., & Lavecchia, A. (2026) · Computer Science Review · doi:10.1016/j.cosrev.2026.100943 · Cited by 23
Molecular Origin of Blood‐Based Infrared Spectroscopic Fingerprints**
Voronina, L., Leonardo, C., Mueller‐Reif, J. B., Geyer, P. E., Huber, M., Trubetskov, M. K., Kepesidis, K. V., Behr, J., Mann, M., Krausz, F., et al. (2021) · Angewandte Chemie · doi:10.1002/ange.202103272 · Cited by 15
Prediction of narrow HT-SMA thermal hysteresis behaviour using explainable machine learning
Machaka, R., & Radingoana, P. M. (2023) · Materials Today Communications · doi:10.1016/j.mtcomm.2023.105806 · Cited by 21
de Bosscher, B. C. D., Ziabari, S. S. M., & Sharpanskykh, A. (2023) · Simulation Modelling Practice and Theory · doi:10.1016/j.simpat.2023.102811 · Cited by 19
Digital Soil Mapping: concepts, methods, and applications - Remote sensing and GIS perspectives
Mondal, B. P., Sahoo, R. N., Das, B., Chakraborty, D., Kumar, N., & Raj, G. B. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-18773-5.00018-1 · Cited by 17
How far are we with automated machine learning? characterization and challenges of AutoML toolkits
Alamin, M. A. A., & Uddin, G. (2024) · Empirical Software Engineering · doi:10.1007/s10664-024-10450-y · Cited by 18
On Using Explainable Artificial Intelligence for Failure Identification in Microwave Networks
Ayoub, O., Musumeci, F., Ezzeddine, F., Passera, C., & Tornatore, M. (2022) · Conference on Innovation in Clouds, Internet and Networks and Workshops (ICIN) · doi:10.1109/icin53892.2022.9758095 · Cited by 17
Earth Observation Semantic Data Mining: Latent Dirichlet Allocation-Based Approach
Asiyabi, R. M., & Datcu, M. P. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2022.3159277 · Cited by 14
AN EXPLAINABLE CONVOLUTIONAL AUTOENCODER MODEL FOR UNSUPERVISED CHANGE DETECTION
Bergamasco, L., Saha, S., Bovolo, F., & Bruzzone, L. (2020) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xliii-b2-2020-1513-2020 · Cited by 16
“Some of the works towards investigating the explainability of deep learning models is found in (Xue, Chuah, 2019)(Roscher et al., 2019)(Angelov, Soares, 2019).”
Ellinas, P., Karampinis, I., Nadal, I. V., Nellikkath, R., Vorwerk, J., & Chatzivasileiadis, S. (2025) · Sustainable Energy Grids and Networks · doi:10.1016/j.segan.2025.101818 · Cited by 20
Analysis of Failure Features of High-Speed Automatic Train Protection System
Kang, R., Wang, J., Chen, J., Zhou, J., Pang, Y., & Cheng, J. (2021) · IEEE Access · doi:10.1109/access.2021.3113381 · Cited by 14
“Model interpretability refers to the understanding of internal mechanism of a model and understanding level of its results [55].”
BackgroundInterpretability and Optimisation of Convolutional Neural Networks Based on Sinc-Convolution
Habib, A., Karmakar, C. K., & Yearwood, J. L. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3185290 · Cited by 17
“It is often required that ML model’s decision making should be fair and ethical, especially, for medical and other sensitive applications, where it is important to provide reasons for decisions of ML algorithms in order to establish trust on the decision making [3].”
BackgroundMethodHard Law and Soft Law Regulations of Artificial Intelligence in Investment Management
Buczynski, W., Steffek, F., Fabio Cuzzolin, A., Jamnik, M., & Sahakian, B. J. (2022) · Cambridge yearbook of European legal studies · doi:10.1017/cel.2022.10 · Cited by 18
Are Data-Driven Explanations Robust Against Out-of-Distribution Data?
Tang, L., Qiao, F., Ma, M., & Peng, X. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00372 · Cited by 26
Global geometry of chemical graph neural network representations in terms of chemical moieties
El-Samman, A. M., Incé A. Husain, Huynh, M., Castro, S. D., Morton, B., Baerdemacker, S. D., & Baerdemacker, S. D. (2024) · Digital Discovery · doi:10.1039/d3dd00200d · Cited by 23
Explainable Multimodal Learning in Remote Sensing: Challenges and Future Directions
Günther, A., Najjar, H., & Dengel, A. R. (2024) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2024.3404596 · Cited by 14
“The field of eXplainable AI (XAI) is specifically designed to address models interpretability, unveiling insights into the model’s acquired knowledge and the underlying reasoning behind its predictions [4].”
BackgroundChowell, G., & Skums, P. (2024) · Physics of Life Reviews · doi:10.1016/j.plrev.2024.10.011 · Cited by 17
Zahra, E., Mosalpuri, M., Baltrušaitis, J., Dubey, P., & Wright, M. M. (2025) · Sustainability Science and Technology · doi:10.1088/2977-3504/ada77b · Cited by 14
An eigenvalue-driven framework for the ranking and selection of optimal geological CO2 storage sites
Iranfar, S., Sadeghpour, F., Manshad, A. K., Naderi, M., & Shakiba, M. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.106770 · Cited by 15
State of the art of Fairness, Interpretability and Explainability in Machine Learning: Case of PRIM
Nassih, R., & Berrado, A. (2020) · International Conference on Intelligent Systems: Theories and Applications · doi:10.1145/3419604.3419776 · Cited by 20
Ex Ante Predictability of Rapid Growth: A Design Science Approach
Hyytinen, A., Rouvinen, P., Pajarinen, M., & Virtanen, J. (2022) · Entrepreneurship Theory and Practice · doi:10.1177/10422587221128268 · Cited by 19
“We have not focused on the question of variable (predictor) importance, emphasized in the explainable ML literature (e.g., Roscher et al., 2020).”
BackgroundComputational biology: Role and scope in taming antimicrobial resistance
Sharma, P., Dahiya, S., Kaur, P., & Kapil, A. (2023) · Indian Journal of Medical Microbiology · doi:10.1016/j.ijmmb.2022.12.005 · Cited by 13
Ekim, B., Stomberg, T., Roscher, R., & Schmitt, M. (2023) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2022.3226525 · Cited by 10
“Explainable ML approaches, which are used for the discovery of new scientific knowledge, such as the exploration of wildlife characteristics, combine interpretation tools that present complex processes as in neural networks in a human-understandable space with domain knowledge to derive explanations [22].”
Self-citationThe Methods and Approaches of Explainable Artificial Intelligence
Szczepański, M., Choraś, M., Pawlicki, M., & Pawlicka, A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-77970-2_1 · Cited by 14
“Some of them present a general overview of the concept [7][8], while others focus on specific, particular features of the Explainable AI [9][10].”
Kurban, M., Polat, C., Serpedin, E., & Kurban, H. (2026) · Materials & Design · doi:10.1016/j.matdes.2026.116401 · Cited by 14
Ensemble Learning for Blending Gridded Satellite and Gauge-Measured Precipitation Data
Papacharalampous, G., Tyralis, H., Doulamis, N. D., & Doulamis, A. D. (2023) · Remote Sensing · doi:10.3390/rs15204912 · Cited by 13
Khayal, I. S., O’Malley, A. J., & Barnato, A. E. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00925-5 · Cited by 13
Haghi, S., Keilhofer, J., Schwarz, N., He, P., & Daub, R. (2023) · Batteries & Supercaps · doi:10.1002/batt.202300457 · Cited by 15
Knowledge graph-based image classification
Mbiaya, F. A., Vrain, C., Ros, F., Dao, T.-B.-H., & Lucas, Y. (2024) · Data & Knowledge Engineering · doi:10.1016/j.datak.2024.102285 · Cited by 16
Unlocking renewable energy potential: Harnessing machine learning and intelligent algorithms
Le, T. T., Paramasivam, P., Adril, E., Nguyen, V. Q., Le, M. X., Duong, M. T., Le, H. C., & Nguyen, A. Q. (2024) · International Journal of Renewable Energy Development · doi:10.61435/ijred.2024.60387 · Cited by 24
“Semi-supervised algorithms fall into another group and enhance learning accuracy by combining labeled and unlabelled input (Roscher et al. , 2020; P. Sharma et al. , 2022a).”
BackgroundWang, Y., Hu, L., Hou, L., Wang, L., Chen, J., He, Y., & Su, X. (2024) · Environment Development and Sustainability · doi:10.1007/s10668-024-05263-4 · Cited by 14
“However, although ML can achieve good results in prediction, it is still challenging to explain the specific contribution of input features to the prediction target and the mechanism of action (Arrieta et al., 2020; Roscher et al., 2020), which means that the prediction model of ML is a "black box".”
A novel physics-constrained neural network: An illustration of ground motion models
Ji, D., Li, C., Zhai, C., & Dong, Y. (2024) · Soil Dynamics and Earthquake Engineering · doi:10.1016/j.soildyn.2024.109071 · Cited by 12
Barnard, A. S. (2021) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2021.100696 · Cited by 17
Customer Churn Prediction on Credit Card Services using Random Forest Method
Miao, X., & Wang, H. (2022) · Advances in economics, business and management research/Advances in Economics, Business and Management Research · doi:10.2991/aebmr.k.220307.104 · Cited by 12
“…discussed customer churns in the past, but most of them failed to use a specific collection of datasets or apply machine learning models, which is a branch of computer science, and is widely used in commercial applications with its goal to let computers “learn” without directly programmed [6].”
BackgroundEfficient forecasting of chaotic systems with block-diagonal and binary reservoir computing
Ma, H., Prosperino, D., Haluszczynski, A., & Rath, C. W. (2023) · Chaos An Interdisciplinary Journal of Nonlinear Science · doi:10.1063/5.0151290 · Cited by 16
Autonome Entdeckung in den chemischen Wissenschaften, Teil I: Fortschritt
Coley, C. W., Eyke, N. S., & Jensen, K. F. (2019) · Angewandte Chemie · doi:10.1002/ange.201909987 · Cited by 12
Li, J., Xie, H., Zhang, J., Li, L., Song, G., Fu, H., Chen, P., Liu, C., Zhang, L., Shi, Z., et al. (2025) · Advances in Applied Energy · doi:10.1016/j.adapen.2025.100239 · Cited by 15
Schulze, M. C., Prakash, N., Gering, K. L., Colclasure, A. M., & Weddle, P. J. (2025) · Journal of Power Sources · doi:10.1016/j.jpowsour.2025.238338 · Cited by 11
Evolutionary Optimization of Physics-Informed Neural Networks: Evo-PINN Frontiers and Opportunities
Wong, J. C., Gupta, A., Ooi, C. C., Chiu, P., Liu, J., & Ong, Y.-S. (2026) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2025.3607749 · Cited by 30
“To substantiate these proposed avenues, we further highlight results from recent literature to showcase the early success of such approaches in addressing the aforementioned challenges in PINN optimization and generalization.”
Wang, Q., & Wang, T. (2026) · Sensor Review · doi:10.1108/sr-08-2025-0613 · Cited by 17
Empowering autonomous indoor navigation with informed machine learning techniques
Uganya, G., Bremnavas, I., Prashanth, K. V., Rajkumar, M., Lalitha, R. V. S., & Singh, C. (2023) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2023.108918 · Cited by 12
Ullah, N., Chou, W. K., Vardanyan, R., Rad, A. A., Shah, V., Torabi, S., AVAVDE, D., Airapetyan, A., Zubarevich, A., Weymann, A., et al. (2023) · Minerva Surgery · doi:10.23736/s2724-5691.23.10130-4 · Cited by 11
Online soft measurement for wastewater treatment system based on hybrid deep learning
Mai, W., Chen, Z., Li, X., Yi, X., Zhao, Y., He, X., Xu, X., & Huang, M. (2023) · Frontiers of Environmental Science & Engineering · doi:10.1007/s11783-024-1780-y · Cited by 11
“As one of the most widely used and simplest AI, machine learning can extract features from independent variables to perform complex modeling processing (Roscher et al., 2020), which has attracted most attention from researchers in recent years.”
BackgroundDeng, C., Sun, P., Yin, X., Zou, J., & Wang, W. (2024) · Journal of Environmental Management · doi:10.1016/j.jenvman.2024.121299 · Cited by 14
Zahir, A., Ali, Z., Al‐Shamayleh, A. S., bas, S. R. A., Mahmood, B., Al-Ghushami, A. H., Adnan, R., & Akhunzada, A. (2024) · Scientific Reports · doi:10.1038/s41598-024-74875-7 · Cited by 11
RetractedSantana, E. J., Ibrahimi, E., Ntalianis, E., Cauwenberghs, N., & Kuznetsova, T. (2024) · International Journal of Molecular Sciences · doi:10.3390/ijms252312905 · Cited by 15
Parduzi, Q., Wermelinger, J., Koller, S. D., Sariyar, M., Schneider, U. C., Raabe, A., & Seidel, K. (2025) · Journal of Medical Internet Research · doi:10.2196/63937 · Cited by 13
“For this reason, we used methods from the emerging field of explainable artificial intelligence (XAI) [18,19].”
Majstorović, J., Giffard‐Roisin, S., & Poli, P. (2022) · Geophysical Journal International · doi:10.1093/gji/ggac369 · Cited by 16
Interpreting acoustic features for the assessment of Alzheimer’s disease using ForestNet
Pérez-Toro, P. A., Rodríguez-Salas, D., Arias‐Vergara, T., Klumpp, P., Schuster, M. E., Nöth, E., Orozco‐Arroyave, J. R., & Maier, A. (2022) · Smart Health · doi:10.1016/j.smhl.2022.100347 · Cited by 20
Hydroclimatic time series features at multiple time scales
Papacharalampous, G., Tyralis, H., Markonis, Y., & Hanel, M. (2023) · Journal of Hydrology · doi:10.1016/j.jhydrol.2023.129160 · Cited by 10
“Moreover, explainable machine learning (see, e.g., the reviews on the relevant methods and strategies by Linardatos et al. 2020; Roscher et al. 2020; Belle and Papantonis 2021) through the computation of feature importance scores is exploited for interpreting the clustering outcomes (and hydroclimatic similarity) and…”
MethodForecasting first-year student mobility using explainable machine learning techniques
Litmeyer, M.-L., & Hennemann, S. (2024) · Review of Regional Research · doi:10.1007/s10037-024-00207-x · Cited by 12
“However, there are significant improvements in providing transparent, interpretable, and explainable machine learning methods, in recent years (Miller 2019; Roscher et al. 2020 for comprehensive reviews on the requirements for explainable machine learning).”
Machine Learning–Based Approach for Identifying Research Gaps: COVID-19 as a Case Study
Abd-Alrazaq, A. A., Nashwan, A. J., Shah, Z., Abujaber, A. A., Alhuwail, D., Schneider, J., AlSaad, R., Ali, H., Alomoush, W., Ahmed, A., et al. (2024) · JMIR Formative Research · doi:10.2196/49411 · Cited by 14
“Machine learning (ML) techniques have demonstrated great potential applications of scientific insights and discoveries by addressing challenges related to information retrieval, knowledge discovery, and natural language processing [8].”
BackgroundVALIDATE: A deep dive into vulnerability prediction datasets
Esposito, M., & Falessi, D. (2024) · Information and Software Technology · doi:10.1016/j.infsof.2024.107448 · Cited by 23
Sasikala., S., Arunkumar, S., N, S. S., & S, D. S. S. (2024) · International Conference on Control, Automation and Robotics (ICCAR) · doi:10.1109/iccar61844.2024.10569414 · Cited by 11
“The ML-based chains to provide scientifically explainable outcomes as depicted in Fig.3 was described by Roscher et al. [16] with the following: 1. transparency, 2. interpretability, 3.”
MethodBioM2: biologically informed multi-stage machine learning for phenotype prediction using omics data
Zhang, S., Li, P., Wang, S., Zhu, J., Huang, Z., Cai, F., Freidel, S., Ling, F., Schwarz, E., & Chen, J. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae384 · Cited by 13
“In terms of developing explainable machine learning models, three key terms emerge: transparency, interpretability and explainability [15].”
BackgroundDiverse explanations from data-driven and domain-driven perspectives in the physical sciences
Li, S., Wang, X., & Barnard, A. S. (2024) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ad9137 · Cited by 18
“Empowering scientists to maintain control over the explanation process [26, 30] includes recognising that different stakeholders in scientific contexts often have varied needs and perspectives when employing ML models.”
Influential
Metadata
- Authors
- Roscher, R., Bohn, B., Duarte, M. F., & Garcke, J.
- Affiliations
- University of Bonn (DE)
- University of Massachusetts Amherst (US)
- Venue
- IEEE Access
- Published
- 2020
- Volume
- 8
- Pages
- 42200-42216
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W2945526235
- Cited by
- 1,040
- References
- 137
- Citations by year
- 2026: 152 · 2025: 178 · 2024: 168 · 2023: 184 · 2022: 174 · 2021: 130 · 2020: 47
- FWCI
- 52.58
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft) (submittedVersion, other-oa)
- Fraunhofer-Publica (Fraunhofer-Gesellschaft) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Fraunhofer Cluster of Excellence Cognitive Internet Technologies
- Deutsche Forschungsgemeinschaft
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Social Sciences › Decision Sciences › Information Systems and Management › Scientific Computing and Data Management
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Keywords
- explainable machine learning, scientific discovery, transparency, interpretability, explainability, domain knowledge, observational data, simulated data
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.