arxiv: 2604.12451 · v1 · submitted 2026-04-14 · ❄️ cond-mat.mtrl-sci · physics.app-ph· physics.optics

Recognition: unknown

Enhancing Laser Surface Texturing through Advanced Machine Learning Techniques

Andr\'es Fabi\'an Lasagni, Christoph Zwahr, Frederic Schell, Tobias Steege

Authors on Pith no claims yet

Pith reviewed 2026-05-10 15:17 UTC · model grok-4.3

classification ❄️ cond-mat.mtrl-sci physics.app-phphysics.optics

keywords laser surface texturingmachine learningneural networksrandom forestssurface roughness predictionprocess optimizationpredictive modeling

0 comments

The pith

Machine learning models predict surface roughness from laser parameters in texturing processes.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper applies neural networks and random forests to laser surface texturing. These models learn to forecast the roughness of the resulting surface using inputs like pulse duration, wavelength, and material properties such as heat capacity. This modeling bypasses the need for exhaustive physical experiments to map out how parameters affect the outcome. As a result, process optimization can proceed more rapidly while still achieving accurate predictions of the textured surface.

Core claim

Neural networks and random forests can predict surface roughness based on laser parameters and material data. This enables faster process optimization, reduces experimental effort, and supports predictive visualization while maintaining high accuracy.

What carries the argument

Neural network and random forest regression models trained to map laser and material inputs to surface roughness outputs.

If this is right

Process optimization for specific target surface geometries is accelerated.
Experimental fabrication of numerous parameter sets is minimized.
Surface properties can be visualized predictively before manufacturing.
Accuracy in roughness prediction remains high for practical use.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

These predictions could be used to optimize additional surface properties like friction or adhesion.
Combining the models with sensor data might allow closed-loop control of the laser process.
Transfer of the trained models to different laser systems or materials may require only small additional datasets.

Load-bearing premise

The nonlinear interactions in laser-material processing are learnable by standard neural networks and random forests from limited data without overfitting to training conditions.

What would settle it

Measuring actual surface roughness on samples produced with parameter combinations outside the training data and finding predictions off by more than the claimed accuracy.

Figures

Figures reproduced from arXiv: 2604.12451 by Andr\'es Fabi\'an Lasagni, Christoph Zwahr, Frederic Schell, Tobias Steege.

read the original abstract

Laser material processing has emerged as a versatile and indispensable tool in various industries, including manufacturing, healthcare, and materials science. However, the interaction of a lasers with surfaces is highly dependent on a large number of factors, including properties of the laser source such as pulse duration, wavelength and pulse form, as well as properties of the material such as surface roughness, heat capacity and thermal conductivity. Therefore, the optimization of laser texturing processes in regards to specific target geometries while maintaining texture quality and process efficiency is a time consuming task that requires experienced operators with expert knowledge of the process and its components. The complex and nonlinear relationships between the various process, laser and material parameters and the resulting surface topography or functionality are challenging to model analytically. Therefore, the fabrication of large numbers of different parameter variations are typically required to enable empirical modeling and process optimization. Machine learning offers a promising approach to overcoming these challenges, particularly when the interrelations between process parameters are not well understood. It enables effective process optimization, surface property prediction, and automated monitoring-tasks that previously required expert knowledge. This chapter demonstrates the application of machine learning to Laser Surface Texturing techniques. Using algorithms such as neural networks and random forests, surface roughness can be predicted based on laser parameters and material data. This facilitates faster process optimization, reduces experimental effort, and enables predictive visualization - all while maintaining high accuracy.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

The paper applies neural networks and random forests to predict surface roughness from laser parameters but supplies no quantitative results, dataset details, or validation metrics to support its accuracy claims.

read the letter

Here's the quick read on this one. The paper shows how neural networks and random forests can be used to predict surface roughness in laser surface texturing based on laser and material parameters. It suggests this approach can reduce the need for lots of experiments and help with process optimization. That's the core idea. It does a good job describing the problem. Laser texturing involves many variables like pulse duration, wavelength, and material properties such as thermal conductivity, and these interact in nonlinear ways that are hard to model with simple equations. The motivation for using ML to handle that complexity and speed things up is clear and practical for manufacturing settings. Where it falls short is the lack of any concrete evidence. The text claims the models maintain high accuracy and enable faster optimization, but it doesn't provide dataset sizes, feature lists, model specifics, training procedures, or performance numbers like error rates or R-squared values. There's also no discussion of how the data was split for testing or whether the models generalize to new conditions. This leaves the main claim hanging without support, and it raises the usual worry about whether the results are just from fitting the training data rather than learning real patterns. The methods themselves are not new. Neural nets and random forests are standard for this kind of regression task, and similar work has been done in other laser processing contexts. So this feels like an incremental case study rather than something that advances the field. This kind of paper might appeal to engineers or researchers in materials processing who are exploring ML for their own optimization problems. It could give them a sense of what's possible and some high-level guidance. But anyone looking for a detailed study with reproducible results or novel ML contributions won't find it here. I wouldn't push for peer review right now. The missing validation details are too central to the claims. If the authors add the quantitative results, comparisons, and data descriptions, it could be worth a look for a specialized journal in manufacturing or applied ML. Otherwise, it reads more like a preliminary report.

Referee Report

2 major / 2 minor

Summary. The manuscript claims that machine learning algorithms such as neural networks and random forests can predict surface roughness in laser surface texturing from laser parameters (e.g., pulse duration, wavelength) and material properties (e.g., heat capacity, thermal conductivity). It asserts that this enables faster process optimization, reduces the need for extensive empirical trials to model complex nonlinear relationships, and supports predictive visualization while maintaining high accuracy.

Significance. If supported by rigorous validation, the approach could meaningfully accelerate optimization in laser material processing applications across manufacturing and healthcare by replacing or supplementing labor-intensive parameter sweeps with predictive models. This would be particularly valuable where analytical modeling is intractable.

major comments (2)

[Abstract] Abstract: The central assertion that the models predict surface roughness 'while maintaining high accuracy' and reduce experimental effort is unsupported by any quantitative evidence, including dataset size or composition, performance metrics (RMSE, R², etc.), held-out test-set results, error bars, or comparisons to baselines or analytical models.
[Abstract] Abstract: No information is given on model architectures, hyperparameters, feature engineering, training/validation splits, regularization techniques, or cross-validation procedures. Without these details it is impossible to determine whether the claimed capture of nonlinear relationships reflects genuine generalization or overfitting to the training data.

minor comments (2)

[Abstract] Abstract: Grammatical error in 'the interaction of a lasers with surfaces' (should be 'a laser').
[Abstract] Abstract: 'in regards to specific target geometries' should read 'with regard to specific target geometries'.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive and detailed feedback. We agree that the abstract requires substantial strengthening with quantitative evidence and methodological transparency to support the claims made. We will revise the manuscript to address both major comments.

read point-by-point responses

Referee: [Abstract] Abstract: The central assertion that the models predict surface roughness 'while maintaining high accuracy' and reduce experimental effort is unsupported by any quantitative evidence, including dataset size or composition, performance metrics (RMSE, R², etc.), held-out test-set results, error bars, or comparisons to baselines or analytical models.

Authors: We agree that the abstract currently lacks the quantitative backing for the claims of high accuracy and reduced experimental effort. In the revised manuscript we will add explicit performance metrics (including R², RMSE, and any available error bars), dataset size and composition details, held-out test-set results, and direct comparisons to baseline models or analytical approaches where feasible. revision: yes
Referee: [Abstract] Abstract: No information is given on model architectures, hyperparameters, feature engineering, training/validation splits, regularization techniques, or cross-validation procedures. Without these details it is impossible to determine whether the claimed capture of nonlinear relationships reflects genuine generalization or overfitting to the training data.

Authors: We acknowledge that the absence of these details in the abstract prevents proper evaluation of generalization versus overfitting. The revised manuscript will include complete descriptions of the neural network and random forest architectures, hyperparameter choices, feature engineering steps, training/validation/test splits, regularization methods, and cross-validation procedures to demonstrate that the models capture nonlinear relationships through genuine generalization. revision: yes

Circularity Check

0 steps flagged

No derivation chain or self-referential reduction present

full rationale

The paper is a descriptive overview of applying standard ML algorithms (neural networks, random forests) to predict surface roughness from laser/material parameters. No equations, first-principles derivations, fitted parameters presented as independent predictions, uniqueness theorems, or self-citations appear in the provided text. The central assertion that ML 'predicts... while maintaining high accuracy' and 'reduces experimental effort' is a general empirical claim without any load-bearing step that reduces by construction to its own inputs or data. No patterns from the enumerated list are instantiated. This is a standard application paper whose validity rests on unreported experimental details rather than circular logic.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

Only the abstract is available, so the ledger is limited to the high-level assumptions stated there; no specific model architectures, loss functions, or data splits are described.

axioms (1)

domain assumption Machine learning algorithms can effectively model the complex nonlinear relationships between laser parameters, material properties, and resulting surface topography
Explicitly stated in the abstract as the reason analytical modeling fails and ML is promising.

pith-pipeline@v0.9.0 · 5558 in / 1178 out tokens · 54920 ms · 2026-05-10T15:17:59.431340+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

72 extracted references · 66 canonical work pages

[1]

Ränke, R

F. Ränke, R. Baumann, B. Voisiat, A. Fabián Lasagni, High throughput laser surface micro- structuring of polystyrene by combining direct laser interference patterning with polygon scanner technology. Mater. Lett.: X. 14, 100144, (2022). 10.1016/j.mlblux.2022.100144

work page doi:10.1016/j.mlblux.2022.100144 2022
[2]

Roessler, S

F. Roessler, S. Kloetzer, R. Ebert, A. Streek, Overcoming the duty cycle in polygon mirror scanning. Proc. SPIE. Online available https://www.spiedigitallibrary.org/conference- proceedings-of-spie/13356/3041919/Overcoming-the-duty-cycle-in-polygon-mirror- scanning/10.1117/12.3041919.full, (2025). 10.1117/12.3041919

work page doi:10.1117/12.3041919.full 2025
[3]

Hauschwitz, Demonstration of record-breaking speed capabilities in direct laser interference patterning in the UV range (343 nm)

P. Hauschwitz, Demonstration of record-breaking speed capabilities in direct laser interference patterning in the UV range (343 nm). Proc. SPIE, 66. Online available https://www.spiedigitallibrary.org/conference-proceedings-of- spie/13351/3039891/Demonstration-of-record-breaking-speed-capabilities-in-direct-laser- interference/10.1117/12.3039891.full, (20...

work page doi:10.1117/12.3039891.full 2025
[4]

Xiong, Y

S. Ghosh, R. Knoblauch, M. El Mansori, C. Corleto, Towards AI driven surface roughness evaluation in manufacturing: a prospective study. J. Intell. Manuf. 11, (2024). 10.1007/s10845- 024-02493-1

work page doi:10.1007/s10845- 2024
[5]

Pedregosa, G

F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel et al., Scikit-learn: Machine Learning in Python. J. Mach. Learn. Res. 12, 2825–2830, (2011)

2011
[6]

Abadi, A

M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro et al., TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. Online available https://www.tensorflow.org/, Last accessed on 22.05.2025, (2015)

2025
[7]

Paszke, S

A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan et al., PyTorch: An Imperative Style, High-Performance Deep Learning Library, 8024–8035. Online available http://papers.neurips.cc/paper/9015-pytorch-an-imperative-style-high-performance-deep- learning-library.pdf,
[8]

A. O. Ijaola, E. A. Bamidele, C. J. Akisin, I. T. Bello, A. T. Oyatobo, A. Abdulkareem et al., Wettability Transition for Laser Textured Surfaces: A Comprehensive Review. Surf. Interfaces. 21, 100802, (2020). 10.1016/j.surfin.2020.100802

work page doi:10.1016/j.surfin.2020.100802 2020
[9]

Samanta, Q

A. Samanta, Q. Wang, S. K. Shaw, H. Ding, Roles of chemistry modification for laser textured metal alloys to achieve extreme surface wetting behaviors. Mater. Des. 192, 108744, (2020). 10.1016/j.matdes.2020.108744

work page doi:10.1016/j.matdes.2020.108744 2020
[10]

LeCun, Y

Y. LeCun, Y. Bengio, G. Hinton, Deep learning. Nature. 521, 436–444, (2015). 10.1038/nature14539

work page doi:10.1038/nature14539 2015
[11]

Römer, P

G. Römer, P. Bechtold, Electro-optic and Acousto-optic Laser Beam Scanners. Phys. Procedia. 56, 29–39, (2014). 10.1016/j.phpro.2014.08.092

work page doi:10.1016/j.phpro.2014.08.092 2014
[12]

R. A. Alsaigh, Enhancement of Surface Properties Using Ultrashort-Pulsed-Laser Texturing: A Review. Crystals. 14, 353, (2024). 10.3390/cryst14040353

work page doi:10.3390/cryst14040353 2024
[13]

Zhang, H

T. Zhang, H. Hu, Y. Liang, X. Liu, Y. Rong, C. Wu et al., A novel path planning approach to minimize machining time in laser machining of irregular micro-holes using adaptive discrete grey wolf optimizer. Comput. Ind. Eng. 193, 110320, (2024). 10.1016/j.cie.2024.110320

work page doi:10.1016/j.cie.2024.110320 2024
[14]

Yildirim, B

K. Yildirim, B. Nagarajan, T. Tjahjowidodo, S. Castagne, Review of in-situ process monitoring for ultra-short pulse laser micromanufacturing. J. Manuf. Process. 133, 1126–1159, (2025). 10.1016/j.jmapro.2024.12.011

work page doi:10.1016/j.jmapro.2024.12.011 2025
[15]

S. L. Campanelli, F. Lavecchia, N. Contuzzi, G. Percoco, Analysis of Shape Geometry and Roughness of Ti6Al4V Parts Fabricated by Nanosecond Laser Ablation. Micromachines. 9, (2018). 10.3390/mi9070324

work page doi:10.3390/mi9070324 2018
[16]

Moles, I

L. Moles, I. Llavori, A. Aginagalde, G. Echegaray, D. Bruneel, F. Boto, A. Zabala, On the use of machine learning for predicting femtosecond laser grooves in tribological applications. Tribol. Int. 200, 110067, (2024). 10.1016/j.triboint.2024.110067

work page doi:10.1016/j.triboint.2024.110067 2024
[17]

Florian, S

C. Florian, S. V. Kirner, J. Krüger, J. Bonse, Surface functionalization by laser-induced periodic surface structures. J. Laser Appl. 32, 022063, (2020). 10.2351/7.0000103

work page doi:10.2351/7.0000103 2020
[18]

C. P. Chen, S. P. Koh, I. B. Aris, F. C. Albert, S. K. Tiong, Path optimization using Genetic Algorithm in laser scanning system. Int. Symp. Inf. Technol., 1–5, (2008). 10.1109/ITSIM.2008.4632037

work page doi:10.1109/itsim.2008.4632037 2008
[19]

Petit, N

C. Petit, N. Mariaule, S. Wauters, A. de Decker, D. Bruneel, AI-supported prediction of femtosecond laser micromachining parameters. Proceedings of LPM2024 – the 25th International Symposium on Laser Precision Microfabrication, 98–102, (2024). 10.2961/jlmn.2025.02.2003

work page doi:10.2961/jlmn.2025.02.2003 2024
[20]

M. Ji, M. Thangaraj, S. Devaraj, R. Machnik, N. E. Karkalos, P. Karmiris-Obratański, Prediction and optimization kerf width in laser beam machining of titanium alloy using genetic algorithm tuned adaptive neuro-fuzzy inference system. Int. J. Adv. Manuf. Technol. 132, 5873–5893, (2024). 10.1007/s00170-024-13681-x

work page doi:10.1007/s00170-024-13681-x 2024
[21]

Teixidor, M

D. Teixidor, M. Grzenda, A. Bustillo, J. Ciurana, Modeling pulsed laser micromachining of micro geometries using machine-learning techniques. J. Intell. Manuf. 26, 801–814, (2015). 10.1007/s10845-013-0835-x

work page doi:10.1007/s10845-013-0835-x 2015
[22]

Y. Liu, D. Shangguan, L. Chen, C. Su, J. Liu, Prediction of Femtosecond Laser Etching Parameters Based on a Backpropagation Neural Network with Grey Wolf Optimization Algorithm. Micromachines. 15, (2024). 10.3390/mi15080964

work page doi:10.3390/mi15080964 2024
[23]

C. Vo, B. Zhou, X. Yu, Optimization of laser processing parameters through automated data acquisition and artificial neural networks. J. Laser Appl. 33, 042025, (2021). 10.2351/7.0000455

work page doi:10.2351/7.0000455 2021
[24]

S. Tani, Y. Kobayashi, Ultrafast laser ablation simulator using deep neural networks. Sci. Rep. 12, 5837, (2022). 10.1038/s41598-022-09870-x

work page doi:10.1038/s41598-022-09870-x 2022
[25]

D. J. Heath, J. A. Grant-Jacob, Y. Xie, B. S. Mackay, J. A. G. Baker, R. W. Eason, B. Mills, Machine learning for 3D simulated visualization of laser machining. Opt. Express. 26, 21574, (2018). 10.1364/OE.26.021574

work page doi:10.1364/oe.26.021574 2018
[26]

M. D. T. McDonnell, J. A. Grant-Jacob, M. Praeger, R. W. Eason, B. Mills, Identification of spatial intensity profiles from femtosecond laser machined depth profiles via neural networks. Opt. Express. 29, 36469–36486, (2021). 10.1364/OE.431441

work page doi:10.1364/oe.431441 2021
[27]

Mills, D

B. Mills, D. J. Heath, J. A. Grant-Jacob, R. W. Eason, Predictive capabilities for laser machining via a neural network. Opt. Express. 26, 17245–17253, (2018). 10.1364/OE.26.017245

work page doi:10.1364/oe.26.017245 2018
[28]

P. G. Benardos, G.-C. Vosniakos, Predicting surface roughness in machining: a review. Int. J. Mach. Tools Manuf. 43, 833–844, (2003). 10.1016/S0890-6955(03)00059-2

work page doi:10.1016/s0890-6955(03)00059-2 2003
[29]

J. T. Cardoso, A. I. Aguilar-Morales, S. Alamri, D. Huerta-Murillo, F. Cordovilla, A. F. Lasagni, J. L. Ocaña, Superhydrophobicity on hierarchical periodic surface structures fabricated via direct laser writing and direct laser interference patterning on an aluminium alloy. Opt. Lasers Eng. 111, 193–200, (2018). 10.1016/j.optlaseng.2018.08.005

work page doi:10.1016/j.optlaseng.2018.08.005 2018
[30]

Milles, B

S. Milles, B. Voisiat, M. Nitschke, A. F. Lasagni, Influence of roughness achieved by periodic structures on the wettability of aluminum using direct laser writing and direct laser interference patterning technology. J. Mater. Process. Technol. 270, 142–151, (2019). 10.1016/j.jmatprotec.2019.02.023

work page doi:10.1016/j.jmatprotec.2019.02.023 2019
[31]

Sedlaček, B

M. Sedlaček, B. Podgornik, J. Vižintin, Correlation between standard roughness parameters skewness and kurtosis and tribological behaviour of contact surfaces. Tribol. Int. 48, 102–112, (2012). 10.1016/j.triboint.2011.11.008

work page doi:10.1016/j.triboint.2011.11.008 2012
[32]

A. Dunn, K. L. Wlodarczyk, J. V. Carstensen, E. B. Hansen, J. Gabzdyl, P. M. Harrison et al., Laser surface texturing for high friction contacts. Appl. Surf. Sci. 357, 2313–2319, (2015). 10.1016/j.apsusc.2015.09.233

work page doi:10.1016/j.apsusc.2015.09.233 2015
[33]

Vercillo, S

V. Vercillo, S. Tonnicchia, J.-M. Romano, A. García‐Girón, A. I. Aguilar‐Morales, S. Alamri et al., Design Rules for Laser‐Treated Icephobic Metallic Surfaces for Aeronautic Applications. Adv. Funct. Mater. 30, 1910268, (2020). 10.1002/adfm.201910268

work page doi:10.1002/adfm.201910268 2020
[34]

Steege, G

T. Steege, G. Bernard, P. Darm, T. Kunze, A. F. Lasagni, Prediction of Surface Roughness in Functional Laser Surface Texturing Utilizing Machine Learning. Photonics. 10, 361, (2023). 10.3390/photonics10040361

work page doi:10.3390/photonics10040361 2023
[35]

Advances in Neural Information Processing Systems 32, (2019): Curran Associates, Inc

2019
[36]

B. Wang, P. Wang, J. Song, Y. C. Lam, H. Song, Y. Wang, S. Liu, A hybrid machine learning approach to determine the optimal processing window in femtosecond laser-induced periodic nanostructures. J. Mater. Process. Technol. 308, 117716, (2022). 10.1016/j.jmatprotec.2022.117716

work page doi:10.1016/j.jmatprotec.2022.117716 2022
[37]

X. Li, H. Wang, B. Wang, Y. Guan, Machine learning methods for prediction analyses of 4H– SiC microfabrication via femtosecond laser processing. J. Mater. Res. Technol. 18, 2152–2165, (2022). 10.1016/j.jmrt.2022.03.124

work page doi:10.1016/j.jmrt.2022.03.124 2022
[38]

Leyendecker, M

L. Leyendecker, M. Zuric, M. A. Nazar, K. Johannes, R. H. Schmitt, Predictive Quality Modeling for Ultra-Short-Pulse Laser Structuring utilizing Machine Learning. Procedia CIRP. 117, 275– 280, (2023). 10.1016/j.procir.2023.03.047

work page doi:10.1016/j.procir.2023.03.047 2023
[39]

T. S. Omeje, J. Prada-Rodrigo, E. Gamet, Y. Di Maio, R. Guillemet, T. Itina, X. Sedao, Prediction of Wetting Behaviours of Femtosecond Laser Texturized Surfaces. Proceedings of LPM2024 — the 25th International Symposium on Laser Precision Microfabrication, (2024)

2024
[40]

Mesquita-Guimarães, N

J. Mesquita-Guimarães, N. M. Ferreira, R. Reis, J. Gonzalez-Julian, J. Pinho-da-Cruz, Laser surface texturing and numerical simulation of heat flux on Cr2AlC MAX phase heat exchangers. J. Eur. Ceram. Soc. 43, 5894–5903, (2023). 10.1016/j.jeurceramsoc.2023.06.031

work page doi:10.1016/j.jeurceramsoc.2023.06.031 2023
[41]

N. B. Dahotre, S. R. Paital, A. N. Samant, C. Daniel, Wetting behaviour of laser synthetic surface microtextures on Ti-6Al-4V for bioapplication. Phil. Trans. R. Soc. A. 368, 1863–1889, (2010). 10.1098/rsta.2010.0003

work page doi:10.1098/rsta.2010.0003 2010
[42]

I. S. Omeje, T. E. Itina, Numerical study of the wetting dynamics of droplet on laser textured surfaces: Beyond classical Wenzel and Cassie-Baxter model. Appl. Surf. Sci. Adv. 9, 100250, (2022). 10.1016/j.apsadv.2022.100250

work page doi:10.1016/j.apsadv.2022.100250 2022
[43]

Baronti, A

L. Baronti, A. Michalek, M. Castellani, P. Penchev, T. L. See, S. Dimov, Artificial neural network tools for predicting the functional response of ultrafast laser textured/structured surfaces. Int. Symp. Inf. Technol. 119, 3501–3516, (2022). 10.1007/s00170-021-08589-9

work page doi:10.1007/s00170-021-08589-9 2022
[44]

S. Choi, K. Kim, K. Byun, J. Jang, Machine-Learning Approach in Prediction of the Wettability of a Surface Textured with Microscale Pillars. Langmuir. 39, 17471–17479, (2023). 10.1021/acs.langmuir.3c02688

work page doi:10.1021/acs.langmuir.3c02688 2023
[45]

Zhang, Z

Z. Zhang, Z. Yang, Z. Zhao, Y. Liu, C. Wang, W. Xu, Multimodal Deep-Learning Framework for Accurate Prediction of Wettability Evolution of Laser-Textured Surfaces. ACS Appl. Mater. Interfaces. 15, 10261–10272, (2023). 10.1021/acsami.2c21439

work page doi:10.1021/acsami.2c21439 2023
[46]

H. Na, J. Yoo, H. Ki, Prediction of surface morphology and reflection spectrum of laser-induced periodic surface structures using deep learning. J. Manuf. Process. 84, 1274–1283, (2022). 10.1016/j.jmapro.2022.11.004

work page doi:10.1016/j.jmapro.2022.11.004 2022
[47]

H. Liu, J. Ge, S. Yang, L. Zhang, Y. Xue, J. Lan, Reflection Coefficient Estimation of Femtosecond Laser Surface Processing Using Support Vector Regression. IEEE Photonics J. 14, 1–9, (2022). 10.1109/JPHOT.2022.3214238

work page doi:10.1109/jphot.2022.3214238 2022
[48]

Zhang, K

W. Zhang, K. Gao, X. Li, H. Li, J. Liao, S. Xuan, G. Li, Enhancing antibacterial properties of PEEK surfaces: Laser-induced and machine-learning assessed. Appl. Phys. Lett. 125, 151603, (2024). 10.1063/5.0219141

work page doi:10.1063/5.0219141 2024
[49]

Zhang, T

X. Zhang, T. He, D. Wen, T. Li, X. Chen, C. Li et al., Improving zirconia ceramics grinding surface integrity through innovative laser bionic surface texturing. Ceram. Int. 50, 32081–32097, (2024). 10.1016/j.ceramint.2024.06.012

work page doi:10.1016/j.ceramint.2024.06.012 2024
[50]

K. A. Nur Najwa, Z. Najihah, S. N. Aqida, I. Ismail, M. S. Salwani, Laser Texturing of Soda Lime Glass Surface for Hydrophobic Surface in Wenzel State. Int. J. Automot. Mech. Eng. 21, 10968–10980, (2024). 10.15282/ijame.21.1.2024.02.0848

work page doi:10.15282/ijame.21.1.2024.02.0848 2024
[51]

Schell, R

F. Schell, R. Helbig, F. Bouchard, C. Zwahr, L. D. Renner, A. F. Lasagni, Embossed sub-micron DLIP and LIPSS textures on polypropylene delay surface colonization of Staphylococcus aureus. Mater. Lett. 379, 137722, (2025). 10.1016/j.matlet.2024.137722

work page doi:10.1016/j.matlet.2024.137722 2025
[52]

Müller-Meskamp, Y

L. Müller-Meskamp, Y. H. Kim, T. Roch, S. Hofmann, R. Scholz, S. Eckardt et al., Efficiency enhancement of organic solar cells by fabricating periodic surface textures using direct laser interference patterning. Adv. Mater. 24, 906–910, (2012). 10.1002/adma.201104331

work page doi:10.1002/adma.201104331 2012
[53]

Berger, M

J. Berger, M. Grosse Holthaus, N. Pistillo, T. Roch, K. Rezwan, A. F. Lasagni, Ultraviolet laser interference patterning of hydroxyapatite surfaces. Appl. Surf. Sci. 257, 3081–3087, (2011). 10.1016/j.apsusc.2010.10.120

work page doi:10.1016/j.apsusc.2010.10.120 2011
[54]

Pfleging, R

W. Pfleging, R. Kumari, H. Besser, T. Scharnweber, J. D. Majumdar, Laser surface textured titanium alloy (Ti–6Al–4V): Part 1 – Surface characterization. Appl. Surf. Sci. 355, 104–111, (2015). 10.1016/j.apsusc.2015.06.175

work page doi:10.1016/j.apsusc.2015.06.175 2015
[55]

L. M. Vilhena, M. Sedlaček, B. Podgornik, J. Vižintin, A. Babnik, J. Možina, Surface texturing by pulsed Nd:YAG laser. Tribol. Int. 42, 1496–1504, (2009). 10.1016/j.triboint.2009.06.003

work page doi:10.1016/j.triboint.2009.06.003 2009
[56]

Nečas, P

D. Nečas, P. Klapetek, Gwyddion: an open-source software for SPM data analysis. Open Phys. 10, 181–188, (2012). 10.2478/s11534-011-0096-2

work page doi:10.2478/s11534-011-0096-2 2012
[57]

Online available https://www.digitalsurf.com/software-solutions/profilometry/, Last accessed on 11.12.2024, (2024)

Digital Surf, MountainsMap® for Profilometry. Online available https://www.digitalsurf.com/software-solutions/profilometry/, Last accessed on 11.12.2024, (2024)

2024
[58]

Schell, C

F. Schell, C. Zwahr, A. F. Lasagni, Surfalize: A Python Library for Surface Topography and Roughness Analysis Designed for Periodic Surface Structures. Nanomaterials. 14, (2024). 10.3390/nano14131076

work page doi:10.3390/nano14131076 2024
[59]

Schmitt, T

R. Schmitt, T. Pfeifer, G. Mallmann, Machine integrated telecentric surface metrology in laser structuring systems. ACTA IMEKO. 2, 73, (2014). 10.21014/acta_imeko.v2i2.106

work page doi:10.21014/acta_imeko.v2i2.106 2014
[60]

Thomas, E

R. Thomas, E. Westphal, G. Schnell, H. Seitz, Machine Learning Classification of Self- Organized Surface Structures in Ultrashort-Pulse Laser Processing Based on Light Microscopic Images. Micromachines. 15, (2024). 10.3390/mi15040491

work page doi:10.3390/mi15040491 2024
[61]

Mills, D

B. Mills, D. J. Heath, J. A. Grant-Jacob, Y. Xie, R. W. Eason, Image-based monitoring of femtosecond laser machining via a neural network. J. Phys. Photonics. 1, 15008, (2019). 10.1088/2515-7647/aad5a0

work page doi:10.1088/2515-7647/aad5a0 2019
[62]

Y. Xie, D. J. Heath, J. A. Grant-Jacob, B. S. Mackay, M. D. T. McDonnell, M. Praeger et al., Deep learning for the monitoring and process control of femtosecond laser machining. J. Phys. Photonics. 1, 35002, (2019). 10.1088/2515-7647/ab281a

work page doi:10.1088/2515-7647/ab281a 2019
[63]

Miotello, R

A. Miotello, R. Kelly, Laser-induced phase explosion: new physical problems when a condensed phase approaches the thermodynamic critical temperature. Appl. Phys. A. 69, S67-S73, (1999). 10.1007/s003399900296

work page doi:10.1007/s003399900296 1999
[64]

Q. Lu, S. S. Mao, X. Mao, R. E. Russo, Delayed phase explosion during high-power nanosecond laser ablation of silicon. Appl. Phys. Lett. 80, 3072–3074, (2002). 10.1063/1.1473862

work page doi:10.1063/1.1473862 2002
[65]

von der Linde, K

D. von der Linde, K. Sokolowski-Tinten, The physical mechanisms of short-pulse laser ablation. Appl. Surf. Sci. 154-155, 1–10, (2000). 10.1016/S0169-4332(99)00440-7

work page doi:10.1016/s0169-4332(99)00440-7 2000
[66]

T. S. Omeje, J. Prada-Rodrigo, E. Gamet, Y. Di Maio, R. Guillemet, T. Itina, X. Sedao, Femtosecond laser micromachining of diamond: Current research status, applications and challenges. Carbon. 179, 209–226, (2021). 10.1016/j.carbon.2021.04.025

work page doi:10.1016/j.carbon.2021.04.025 2021
[67]

D. J. Förster, B. Jäggi, A. Michalowski, B. Neuenschwander, Review on Experimental and Theoretical Investigations of Ultra-Short Pulsed Laser Ablation of Metals with Burst Pulses. Materials (Basel, Switzerland). 14, (2021). 10.3390/ma14123331

work page doi:10.3390/ma14123331 2021
[68]

J. A. Grant-Jacob, B. Mills, M. N. Zervas, Acoustic and plasma sensing of laser ablation via deep learning. Opt. Express. 31, 28413–28422, (2023). 10.1364/OE.494700

work page doi:10.1364/oe.494700 2023
[69]

Steege, S

T. Steege, S. Alamri, A. F. Lasagni, T. Kunze, Detection and analysis of photo-acoustic emission in Direct Laser Interference Patterning. Sci. Rep. 11, 14540, (2021). 10.1038/s41598-021-93927- w

work page doi:10.1038/s41598-021-93927- 2021
[70]

H. J. Langeheinecke, S. Tutunjian, M. Soldera, T. Wegner, A. F. Lasagni, Analyzing the Electromagnetic Radiations Emitted during a Laser-based Surface Pre-Treatment Process for Aluminium using Diode Sensors as an Approach for High-Resolution Online Monitoring. JLMN, (2022). 10.2961/jlmn.2022.03.2002

work page doi:10.2961/jlmn.2022.03.2002 2022
[71]

J. A. Grant-Jacob, B. Mills, M. N. Zervas, Live imaging of laser machining via plasma deep learning. Opt. Express. 31, 42581–42594, (2023). 10.1364/OE.507708

work page doi:10.1364/oe.507708 2023
[72]

J. A. Grant-Jacob, B. Mills, M. N. Zervas, Real-time control of laser materials processing using deep learning. Manuf. Lett. 38, 11–14, (2023). 10.1016/j.mfglet.2023.08.145

work page doi:10.1016/j.mfglet.2023.08.145 2023