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 901–999 of 999
Wu, T., & Han, Z. (2025) · Physica A Statistical Mechanics and its Applications · doi:10.1016/j.physa.2025.131077 · Cited by 2
Machine Learning for Optical Network: A Survey
Srivastava, S., Singh, A., Verma, P. K., Kumar, L., Vishwakarma, P., & Pandey, D. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-7249-3_33
Darling, D., Bhattarai, Y., Kamanmalek, S., Talchabhadel, R., & Sharma, S. (2025) · Scientific Reports · doi:10.1038/s41598-025-24213-2 · Cited by 4
Corrales-González, M., Gorr-Pozzi, E., & Giorgi, G. (2025) · IEEE International Workshop on Metrology for the Sea; Learning to Measure Sea Health Parameters (MetroSea) · doi:10.1109/metrosea66681.2025.11245729
Soil, Climate, and Food Security: Strategies and Sustainable Solutions for Global Nourishment
Shukla, S., Patil, S. D., Pravin, G., Phutela, S., & Shukla, S. K. (2025) · Springer eBooks · doi:10.1007/978-3-032-07096-8_11
Ma, F.-Q., He, C., Yang, H.-R., Hu, Z.-W., Mao, H.-R., Fan, C.-Y., Qi, Y., Zhang, J.-X., & Xu, B. (2023) · Figshare · doi:10.6084/m9.figshare.24054343
Papacharalampous, G., Tyralis, H., Markonis, Y., Máca, P., & Hanel, M. (2024) · Figshare · doi:10.6084/m9.figshare.26609364
Advances in understanding antimicrobial resistance and approaches for mitigation
Mobarki, M. I., Alkaabi, A. A., Alqahtani, M. H., Alasmri, W. A., Alkhuwaiter, N. F., Alasmary, S. A., Alghamdi, D. S., Alsharidah, I. A., Alhakami, A. M. A., Almohaimeed, R. M., et al. (2025) · Journal Of Advanced Pharmacy Education And Research · doi:10.51847/5p5jo37fex
Vaitheeshwari, R., Kao, C.-C., Wu, R.-X., Chen, C., Tsai, P., Shih-Ching, Y., & Wu, E. H. (2026) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2025.3650378
“Users can gain insights into how the model generates results by considering factors such as the allocation of feature weights or model parameter design [17], [18].”
Designing Interpretable Machine Learning Prediction Model for Crime Prediction in Montgomery County
Reehl, A. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-981-95-1353-6_26
Explainable Machine Learning for Transparent Decision-Making in E-Governance Systems
Ghosh, S., Shukla, V. K., Chanda, P., & Singh, A. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-12232-2_19 · Cited by 1
Educable Learning for Human-AI Coevolution
Vanderhaegen, F. (2026) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-14055-5_8
AI-Augmented Financial Ratio Analysis for Early Warning, Monitoring, and Assurance
Mohammad, Y., Mohamed, E. A., & Nachouki, M. (2025) · International Conference on Signal Processing and Information Security (ICSPIS) · doi:10.1109/icspis67605.2025.11318382 · Cited by 2
“Provide both global and local explanations (such as feature attributions) for analyst review; maintain audit trails of algorithms (including model cards, slice performance, and bias checks) to align with governance requirements [11], [12], [14].”
InfluentialExplainable Artificial Intelligence for Crime Prediction in Montgomery County
Reehl, A., & Yang, B. (2025) · IEEE International Conference on Big Data and Artificial Intelligence (BDAI) · doi:10.1109/bdai66031.2025.11325486
Predicting Moral Values in Lyrics Through Audio
Saitis, C., Heyderman, B., Preniqi, V., †, K. Y. K., & Pauwels, J. (2025) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi66578.2025.11339267
“We used Shapley Additive Global importancE (SAGE) [39] and SHapley Additive exPlanations (SHAP) [40] to interpret our best models’ general behaviour and the importance of different audio features, contributing to explainable machine learning [24], [41].”
Functional Learning: A Physics-Guided Genetic Programming Framework for Engineering Data ModelingPreprint
Luo, C., & Han, G. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6179145
Гребенщикова, Е. Г. (2025) · Scientific and Technical Information Processing · doi:10.3103/s0147688225700777 · Cited by 1
“…they encounter rejections or critical reviews generated by obscure algorithms, which poses the reliability and accountability of AI-based peer review as questionable, at least until the challenges of quickly detecting and correcting inaccuracies or biases in automated systems are addressed [18].”
Explainable AI for Environmental Solutions: Building Trust and Transparency in Quantum Systems
Jeyalakshmi, P. (2026) · Springer eBooks · doi:10.1007/978-3-032-15188-9_11
Quayson, F. (2026) · Research Square · doi:10.21203/rs.3.rs-8913300/v1
SHAP-Enhanced Random Forest Model for Diabetes Prediction
Kaur, V., Batth, J. S., & Pundir, M. (2025) · International Conference on Artificial Intelligence for Innovations in Healthcare Industries (ICAIIHI) · doi:10.1109/icaiihi67124.2025.11403243
“Model outputs also need to be interpreted, data quality ensured and relevant features and algorithms selected to create trustworthy AI systems to predict diabetes [19].”
Kolmogorov-Arnold network driven soft sensors for chemical processes with distributed output
Guo, W., Liu, A., Jia, M., & Liu, Y. (2026) · Computers & Chemical Engineering · doi:10.1016/j.compchemeng.2026.109612
Malarvel, M., Kaliyamurthie, K. P., & Antonidoss, A. (2025) · IEEE International Conference on Innovations in Engineering and Next-Generation Technologies for Sustainability (ICINVENTS) · doi:10.1109/icinvents64613.2025.11402497
“A concept of explainability by design is being more and more recognized as a best practice in classical and quantum machine learning research [10].”
Ajai Krishna, T. S., Sunil Kumar, S., & S, A. V. (2026) · International Conference on Mobile Computing and Sustainable Informatics (ICMCSI) · doi:10.1109/icmcsi67283.2026.11412496
“A few recent efforts use SHAP values to explain rainfall–runoff predictions or climate model outputs [16], [17], but comprehensive integration of XAI with multi-modal hydrological forecasting frameworks remains largely unexplored.”
Do Deeper Layers Explain Better? An LID-Based Study of Transformer Explainability
Roufas, N., Kanavos, A., Karamitsos, I., Al-Hussaeni, K., & Μaragoudakis, M. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11402387
“Foundational surveys have categorized XAI approaches along three key dimensions: interpretability target (global vs. local), methodological type (post-hoc vs. inherently interpretable), and model dependency (agnostic vs. model-specific) [1], [61].”
Onyekachi, N. S., Yu, Q., Liu, L., Wang, Y., Ikeogu, C. F., Zhang, M., & Chen, N. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6382442
Behavior Learning (BL): Learning Hierarchical Optimization Structures from DataPreprint
Ma, Z., Liang, Y., & Li, D. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6284958
Stucky, B., Scholz, M., Lakaemper, S., Keller, K., Kræmer, T., & Landolt, H. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.111331 · Cited by 1
Amri, F. (2026) · Environmental Economics and Policy Studies · doi:10.1007/s10018-026-00472-9
Leveraging XAI for Semiconductor Electrical - Parameter Characterization Using Machine Learning
Srivastava, S., Roy, D., Srivastava, H., Sehra, K., & Saxena, M. K. (2026) · International Conference on VLSI Design · doi:10.1109/vlsid68508.2026.00060
“From manufacturing and agriculture to healthcare and finance, innovations and ideations are led by algorithmic machine learning that were previously extremely rigorous to perform through the traditional methods [1][2].”
Campos-García, T., Vazquez-Martínez, J., & Campos, H. (2026) · Research Square · doi:10.21203/rs.3.rs-9132922/v1
Assessing and explaining temporal deep learning models for wildfire danger prediction
Becker, P., de Moura, C. N., & Nowack, P. J. (2026) · Machine Learning Earth · doi:10.1088/3049-4753/ae5aa0 · Cited by 2
“Although these results align with intuitive expectations and prior studies [24, 79], caution is warranted to avoid confirmation biases [106].”
Novello, P. (2022) · theses.fr (ABES) · doi:10.70675/fde62335z8ca3z478cz8ddcz466a6a243163 · Cited by 1
Deep learning interpretability with visual analytics : Exploring reasoning and bias exploitation
Jaunet, T. (2022) · theses.fr (ABES) · doi:10.70675/a754696bzcd37z49a2zb2a7z2ad1bfd9b620 · Cited by 1
Automatic learning of interaction networks from next-generation sequence data
Barroso‐Bergadà, D. (2022) · theses.fr (ABES) · doi:10.70675/f05c8901z8d71z4975z85bczbd78bc8097ae
On the use of Machine Learning modeling tools in chemical process and product engineering
Trinh, C. (2023) · theses.fr (ABES) · doi:10.70675/07975f61z019bz4c08zaae4z2fcda6cc9032
Haberle, V. (2023) · theses.fr (ABES) · doi:10.70675/10cc91e5z650dz42b2zb30czd4c84f3939ed · Cited by 1
Żeruń, M., Jagoda, E., & Majer, E. (2026) · Energies · doi:10.3390/en19081827 · Cited by 2
Guo, M., Gong, J., Chen, Y., Jian, Y., Xiao, W., & Wang, S. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6560841
Tao, L., Manalo, E., Jose, H. W., Angeles, O. R., Radanielson, A. M., & Azevedo, L. B. (2026) · Agricultural Water Management · doi:10.1016/j.agwat.2026.110717
Reshaeel, M., Khadkikar, V., & Ali, M. I. H. (2026) · Energy and AI · doi:10.1016/j.egyai.2026.100766
Leveraging LLMs and Graph-RAG for Enhanced Criminal Analysis
Reehl, A., & Yang, B. (2025) · Artificial Intelligence for Business (AIxB) · doi:10.1109/aixb65684.2025.00026
Li, X., Li, P., Pan, H., Kwong, C. F., Bie, J., Ren, Y., Yang, S., Smith, R., & Wang, J. (2026) · Sensors and Actuators Reports · doi:10.1016/j.snr.2026.100473 · Cited by 1
Yu, K., Xu, D., Zhou, Y., He, B., Xiao, F., Li, X., Liao, W., Wu, X., Geng, X., & Feng, Q. (2026) · Ecological Indicators · doi:10.1016/j.ecolind.2026.114923
Gipiškis, R. (2025) · doi:10.15388/vu.thesis.781 · Cited by 1
Short Paper: Towards Algorithmically Grounded Embedded AI Models
Wang, Z., Uddin, M. Y. S., & Nirjon, S. (2026) · Proceedings of the 2026 ACM/IEEE International Conference on Embedded Artificial Intelligence and Sensing Systems · doi:10.1145/3774906.3800495
“AINNs also differ from prior modular or concept-bottleneck designs that introduce structure without aligning to an algorithmic trace [92], and from neural algorithmic reasoning [108] or differentiable operators [31], which emphasize learned operators but provide limited visibility into intermediate…”
Champer, M. I., Singh, V., & Campagnola, P. J. (2026) · Journal of Physics Photonics · doi:10.1088/2515-7647/ae6c77
“An ideal model is transparent, interpretable, and explainable [50].”
LSTM-based Event-Driven Cyber Threat Detection Networks Deep Learning with CICIDS 2018
Priya, V. L., Kumar, J. P., Pannaga, M., Sriteja, S., & Gutam, B. G. (2026) · International Conference on Smart Electronic Devices and Intelligent Systems (ICSEDIS) · doi:10.1109/icsedis68157.2026.11518137
Wei, Q., Tang, Z., LIU, Z., Zhong, J., & Liu, R. (2026) · Discrete and Continuous Dynamical Systems - I Intelligence · doi:10.3934/dcdsi.p260202
Ceballos, R. F., Sangco, R. M. R., & Prahutama, A. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-6259-5.ch001
Pogrebna, G., & Hills, T. T. (2026) · Cambridge University Press eBooks · doi:10.1017/9781108939010.035
Vecchio, M. D. (2026) · Cambridge University Press eBooks · doi:10.1017/9781108939010.043
Sharma, R., Salwan, R., & Sharma, V. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-27465-7.00004-2
Capriotti, S., Genovese, D., Devoto, A., Badreshany, K., Braekmans, D., Mignardi, S., Scardapane, S., & Medeghini, L. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6852564
Ari, M., Emsen, B., Doğan, M., & Şarlar, K. (2026) · Plant Biosystems - An International Journal Dealing with all Aspects of Plant Biology · doi:10.1007/s44473-026-00192-8 · Cited by 2
“By complementing theoretical frameworks with data-driven approaches, ML acts as a catalyst for rapid hypothesis testing and more precise biological modeling (Carleo et al. 2019; Roscher et al. 2020).”
Applications of AI in Organic Chemistry
Khuzaifa, M., Kainat, I., & Zeng, Q. (2026) · ChemistrySelect · doi:10.1002/slct.73624 · Cited by 1
Decoding the “Class Attraction” Effect in Satellite Imagery: A Quantitative Explainable AI Approach
Abrouch, J., Korchiyne, R., Maoulainine, R. C., Dahmani, R., & Alaoui, M. T. (2026) · International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET) · doi:10.1109/iraset68627.2026.11538678
“This methodological void hinders the transition from ”interpretability as a visual aid” to ”interpretability as a diagnostic tool,” a requirement for scientific discovery as defined by Roscher et al. [14].”
Preaching Meaning, Practicing the Motions: A Critical Analysis of XAI Research
van der Linden, I., & Ghebreab, S. (2026) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3805689.3812356
“Moreover, it extends the scope of XAI beyond technical interpretability methods to encompass context in the form of domain knowledge and explanation goals [123].”
Lian, J., Mo, Z., Liu, Z., Peng, B., Chang, M., Wang, X., & Wang, W. (2026) · Remote Sensing · doi:10.3390/rs18122057
Quayson, F., & Dadson, I. Y. (2026) · Research Square · doi:10.21203/rs.3.rs-8913236/v2
Chantzi, V. P., Millington, J., Mariconti, E., & Nakhaeizadeh, S. (2026) · Forensic Science International Synergy · doi:10.1016/j.fsisyn.2026.100712
“Explainability is thus crucial for ensuring accountability, transparency, and fairness in machine learning systems, as it allows stakeholders to (caption on next page) identify and rectify any potential biases or errors present in the models, while also informing algorithm refinement [62,66,67].”
Bai, M., Zhu, M., Zhu, H., Yao, D., Liu, Y., & Ju, J.-W. W. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.105017
Xu, L., Mao, K., Guo, Z., Shi, J. Q., Bateni, S. M., & Yuan, Z. (2026) · Big Earth Data · doi:10.1080/20964471.2026.2680809
Common sense testing and sanity checks in machine learning
Naser, M. Z. (2026) · International Journal of Data Science and Analytics · doi:10.1007/s41060-026-01183-w
“Studies focused on interpretability often discuss verifying that a model’s predictions shift in predictable ways under input transformations with known domain implications [55, 56].”
Machine learning prediction of goat reproductive success in smallholder farming systems
Tuyishime, K., Adewusi, M. A., Mutesi, W., & Ahakundire, P. (2026) · Discover Computing · doi:10.1007/s10791-026-10342-3
“…to not-pregnant class ratio and 25 predictor variables, the effective sample per parameter for complex models such as Random Forest (300 trees, thousands of split parameters) and Neural Networks (over 11,000 learnable weights) is far below the level required for reliable generalisation[26, 34].”
Quayson, F., & Dadson, I. Y. (2026) · Research Square · doi:10.21203/rs.3.rs-8913300/v2
Uddin, A. F. M. N., Hasan, F., Islam, M. M., Akhter, A., & Uddin, M. A. (2026) · International Journal of Information Management Data Insights · doi:10.1016/j.jjimei.2026.100430
Moorty, S. K. (2026) · International Conference on Computational Intelligence and Communication Networks (CICN) · doi:10.1109/cicn70047.2026.11594180
“As businesses are getting increasingly dependent on data-based decision-making, the constraints of the legacy infrastructures make it difficult to rely on large-scale data and employ sophisticated methods of analysis [2].”
Yue, Y., Lu, S., Liu, X., Liu, Y., & Cao, S. (2026) · Sustainability · doi:10.3390/su18147183
Liao, Y., Ye, Y., Kuang, L., Jiang, Y., Deng, B., Han, Y., Li, W., Luo, X., Liu, M., & Guo, X. (2026) · Ecological Indicators · doi:10.1016/j.ecolind.2026.115170
Han, D., Kim, H., Choi, D., & Kim, S. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7151342
Yang, T., Han, F., Zhang, K., Ji, J., & Song, B. (2026) · Review of Palaeobotany and Palynology · doi:10.1016/j.revpalbo.2026.105685
Guo, M., Gong, J., Chen, Y., Jian, Y., Xiao, W., & Wang, S. (2026) · Atmospheric Research · doi:10.1016/j.atmosres.2026.109226
Sengupta, S., Sarkar, A., Paul, A., Pandit, M. K., Chattopadhyay, A., Patra, K., Pandit, R., & Biswas, B. (2026) · Journal of Agriculture and Food Research · doi:10.1016/j.jafr.2026.103170
Intelligent Carbon-Aware Gateway Placement for Green IoT Networks
Alvarado-Alcon, F.-J., Asorey-Cacheda, R., García-Haro, J., & García-Sánchez, A.-J. (2026) · Future Internet · doi:10.3390/fi18080389
“Moreover, domain knowledge and explainability are often viewed as necessary ingredients to achieve scientific consistency and to obtain scientifically meaningful outcomes beyond raw predictive performance [12,13].”
Interpretation of Computer Vision Models in Mapping of Opencast Mining Sites: Overview
Колесников, А. А., Reznik, A. V., БЕЛОСЛУДЦЕВА, А. А., ГАВРИЛОВ, В. Л., & МЕДВЕДЕВА, К. Е. (2026) · Journal of Mining Science · doi:10.1134/s1062739126020146
“For example, a building detection model trained on satellite imagery may inadvertently associate certain shadows or road patterns with rooftops, leading to incorrect decisions in regions with different urban layouts [3].”
Demir, C., Gomez‐Velez, J. D., Guimond, J., McClelland, J. W., Charette, M. A., & Cardenas, M. B. (2026) · Geophysical Research Letters · doi:10.1029/2026gl123641
“XAI allows extraction of human‐comprehensible non‐linear input‐output hydrological relationships and support interpretation using contextual information and domain knowledge (Althoff et al., 2021; Başağaoğlu et al., 2022; Biran & Cotton, 2017; Roscher et al., 2020).”
Borderon, J., Gasc‐Barbier, M., & Merrien‐Soukatchoff, V. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7213795
Explainable AI for Graph-Based Drug Discovery Using Deep Learning
Sahu, A., Kumar, N., Pandey, A. K., Tiwary, A., Spoorthi, G. S., & Jahnavi, S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-23716-3_23
Alrawi, B., Mao, X., & Huang, W. (2026) · Journal of Petroleum Geology · doi:10.1111/jpg.70099
Luo, S., Lu, C., & Han, Z. (2026) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2026.3719313
“This mechanism not only capi-talizes on the scenario advantages of nonlinear partitioning but also preserves the underlying physical boundary constraints [18], [19], thereby achieving precise retrieval of ground visibility grades under extreme weather conditions.”
Onyekachi, N. S., Yu, Q., Liu, L., Wang, Y., Ikeogu, C. F., Zhang, M., & Chen, N. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7233260
A Review of Physics-Informed and Data-Driven Surrogate Models for Power Transformer Fault Diagnosis
Wan, G., Yang, K., Xiong, F., & Chen, J. (2026) · Sensors · doi:10.3390/s26155007
“However, strong correlations among gases, derived ratios, and operating variables may redistribute attribution values, and feature contribution should not be interpreted directly as fault causality [82].”
Application of computational methodologies in 2D nanomaterials
Bali, İ., Baysal, T., Doğancı, M., Sarıkaya, M., Temel, M., TOPAÇLI, H., Yazkan, E., & Velioğlu, S. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-44530-9.00007-9
Kushwaha, N. L., Biwalkar, N., Sur, K., Subeesh, A., Patel, A., & Bhattacharjee, S. (2026) · Environmental Management Smart Solutions · doi:10.1016/j.jemss.2026.100001 · Cited by 1
Lv, D., Gao, Q., Wang, S.-L., Du, B.-B., Du, Y.-C.-Z., & Zhang, S. (2026) · Land · doi:10.3390/land15081465
Wang, J., Huang, X., Yang, C., & Liu, Y. (2026) · Sustainability · doi:10.3390/su18168390
Bonito, L. P. D., Campanile, L., Iacono, M., Ragione, E. D., & Natale, F. D. (2026) · Water Research · doi:10.1016/j.watres.2026.126722
An explainable machine learning analysis of retail renewable premiums
Ji, Y., Dormady, N., Shafieezadeh, A., DiAna, K., Hoyt, M., Lamadrid, A. J., & Fox, S. M. (2026) · Energy Economics · doi:10.1016/j.eneco.2026.109554
Oh, H., Baek, S.-S., & Hur, J. (2026) · Environmental Technology & Innovation · doi:10.1016/j.eti.2026.105166
Hridoy, M. W., Amin, F., Hasan, A., Kariya, K., & Miyara, A. (2026) · International Journal of Heat and Mass Transfer · doi:10.1016/j.ijheatmasstransfer.2026.129387
Cheng, M., Khitam, A. F. K., & Liou, J.-W. (2026) · Journal of Computing in Civil Engineering · doi:10.1061/jccee5.cpeng-7843
Quantum‐Trained AI Enables Inverse Design of Organic Frontier Orbitals at Billion‐Scale
Ko, Y., Kim, S. J., & Kim, K. C. (2026) · Advanced Science · doi:10.1002/advs.77414
Islam, M. S., Fares, A., Awal, R., Veettil, A. V., Rahman, A., Mishra, A., Mohtar, R. H., & Sharara, M. A. (2026) · Agricultural Water Management · doi:10.2139/ssrn.7349883
Zheng, W., Sun, A., Wang, H., Wang, Q., Song, K., Feng, H., & Liu, R. (2026) · Buildings · doi:10.3390/buildings16173437
“Previous studies have highlighted that purely data-driven models may suffer from limited interpretability when the relationship between input variables and underlying physical mechanisms is unclear [17].”
Go, S.-H., & Shin, J. H. (2026) · Ecological Informatics · doi:10.1016/j.ecoinf.2026.104020
Synergistic effects of fertilization and climate change on increasing nitrate loading in China
Wu, R., Jia, B., You, Y., Wang, L., Wang, Y., Peng, Q., Ouyang, W., & Xie, Z. (2026) · Journal of Environmental Management · doi:10.1016/j.jenvman.2026.130773
Hakkenberg, C. R., Goetz, S. J., Kerhoulas, L. P., Koch, G. W., van Mantgem, P. J., Adamson, A., Phrakonkham, T., & Wright, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7384236
A bibliometric review of blue carbon ecosystem restoration technologies
Ai, Y., & Cui, Y. (2026) · Regional Studies in Marine Science · doi:10.1016/j.rsma.2026.105410
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.