pith. sign in

arxiv: 2606.18295 · v1 · pith:XMF6NDPYnew · submitted 2026-06-15 · 🧬 q-bio.QM

Archetypal Microbiome Profiles as Indicators of Nitrous Oxide Emission States in Activated Sludge

Cheng Chen , Marcelo Seppi , Samir Suweis , Andreas Froemelt , Eberhard Morgenroth , Andreas Scheidegger , Carlo Albert This is my paper

Pith reviewed 2026-06-27 01:56 UTC · model grok-4.3

classification 🧬 q-bio.QM
keywords archetypal analysisactivated sludgenitrous oxidemicrobiome16S rRNAwastewater treatmentN2O emissionscommunity composition
0
0 comments X

The pith

Archetypal analysis of activated sludge microbiomes identifies a community profile linked to high nitrous oxide emissions across two plants without using emission labels in training.

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

The study collects temporal 16S rRNA profiles and N2O measurements from two full-scale Swiss wastewater plants and applies archetypal analysis to genus-level abundance data. Three archetypes explain 63-73 percent of variation and place samples in a simplex where communities appear as mixtures of distinct states. High-emission samples from both plants cluster near one archetype, and time series show elevated weight on that archetype precisely during high-emission intervals. Temperature further organizes the same space, pointing to seasonal influences on emission-associated configurations. The resulting low-dimensional representation supplies an interpretable way to monitor microbiome shifts tied to N2O output.

Core claim

In both WRRFs, three archetypes captured most explainable variation in community composition (63%--73%) and defined a simplex state space in which samples clustered near vertices and edges. Without using emission labels while training, the archetypal state space aligned strongly with binary N2O emission states: high-emission observations in both plants concentrated around a specific archetype, and temporal trajectories showed consistent high weights of this archetype during high-emission periods. Functional summaries suggested site-specific but pathway-relevant interpretations of the high-N2O archetype. Temperature further structured the archetypal state space, indicating seasonal forcing of

What carries the argument

Archetypal analysis, which expresses each microbiome sample as a convex combination of a small set of extremal community profiles that serve as vertices of a simplex state space.

If this is right

  • The high-N2O archetype weight can serve as a real-time indicator of emission regime shifts in operating plants.
  • Functional gene summaries attached to the archetype point to site-dependent microbial pathways driving the emissions.
  • Seasonal temperature changes move samples within the archetype space in ways that predict periods of elevated risk.
  • The low-dimensional simplex supplies a compact description that could be tracked alongside routine process variables.

Where Pith is reading between the lines

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

  • The same unsupervised approach could be applied to other microbial processes in environmental systems where labeled outcome data are scarce.
  • If the high-emission archetype proves consistent across more sites, it could reduce reliance on continuous N2O sensors for risk screening.
  • Combining archetype weights with existing process models might improve short-term emission forecasts without requiring new labeled training sets.

Load-bearing premise

The post-training alignment between the three unsupervised archetypes and binary N2O states reflects a stable biological relationship rather than plant-specific artifacts or the particular number of archetypes and emission threshold chosen.

What would settle it

Repeating the analysis on data from additional plants or with four or more archetypes and finding that the same single archetype no longer concentrates high-emission samples or that its weight no longer tracks emission spikes.

Figures

Figures reproduced from arXiv: 2606.18295 by Andreas Froemelt, Andreas Scheidegger, Carlo Albert, Cheng Chen, Eberhard Morgenroth, Marcelo Seppi, Samir Suweis.

Figure 1
Figure 1. Figure 1: Rescaled reconstruction error (RSS) of the fitted AA model for different numbers of [PITH_FULL_IMAGE:figures/full_fig_p006_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Projection of samples on a ternary simplex, the vertices represent pure archetypes. Each [PITH_FULL_IMAGE:figures/full_fig_p007_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Archetype compositions (weights) of samples over time. The stacked bars are composed [PITH_FULL_IMAGE:figures/full_fig_p009_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: The composition of genus abundance of archetypes, only the 20 most abundant genera are [PITH_FULL_IMAGE:figures/full_fig_p011_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Relationship between influent wastewater temperature and archetype coefficients. Each [PITH_FULL_IMAGE:figures/full_fig_p012_5.png] view at source ↗
read the original abstract

Nitrous oxide (N2O) emissions from water resource recovery facilities (WRRFs) fluctuate over time and can arise from multiple microbial pathways, making source attribution and full-scale prediction difficult. The difficulty is compounded by the high dimensionality of activated sludge microbiomes, whose complex and dynamic community structure can obscure relationships with N2O emission patterns. This study evaluated whether interpretable, low-dimensional representations of activated sludge microbiomes can be correlated with N2O emission states. Temporal 16S rRNA gene amplicon profiles and N2O emission metrics were collected from two full-scale WRRFs in Switzerland. Genus-level relative-abundance profiles were summarized using archetypal analysis (AA), which represents each sample as a convex combination of a small number of interpretable community profiles. In both WRRFs, three archetypes captured most explainable variation in community composition (63%--73%) and defined a simplex state space in which samples clustered near vertices and edges, indicating that community compositions were organized around distinct archetypal states and their mixtures. Without using emission labels while training, the archetypal state space aligned strongly with binary N2O emission states: high-emission observations in both plants concentrated around a specific archetype, and temporal trajectories showed consistent high weights of this archetype during high-emission periods. Functional summaries suggested site-specific but pathway-relevant interpretations of the high-N2O archetype. Temperature further structured the archetypal state space, indicating seasonal forcing of microbiome configurations associated with elevated N2O. Overall, AA provides an interpretable framework to track microbiome regime shifts and may support operational tracking of high-N2O emission states in full-scale WRRFs.

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.

Referee Report

3 major / 1 minor

Summary. The manuscript claims that archetypal analysis of temporal genus-level 16S rRNA profiles from two full-scale Swiss WRRFs produces a three-archetype simplex capturing 63-73% of variance, and that this unsupervised state space aligns with binary N2O emission states (high-emission samples concentrate around one archetype; trajectories track its weight), with temperature additionally structuring the space and site-specific functional interpretations for the high-N2O archetype.

Significance. If the alignment is shown to be robust, the work would demonstrate a useful label-free, interpretable dimensionality-reduction approach for linking microbiome configurations to emission states across plants; the unsupervised training followed by post-hoc observation of alignment and the multi-plant design are strengths that could support operational monitoring applications.

major comments (3)
  1. [Abstract] Abstract: the claim that the archetypal state space 'aligned strongly' with binary N2O emission states is presented without any quantitative measure of concentration (e.g., proportion of high-emission samples near the vertex or distance statistics) or statistical test of the alignment.
  2. [Abstract] Abstract: temperature is explicitly noted to further structure the same simplex, yet no regression, stratification, or partial-correlation analysis is described to evaluate whether the archetype-N2O association is independent of temperature or potentially mediated by seasonal forcing on both community and emissions.
  3. [Abstract] Abstract: the number of archetypes is fixed at three on the basis of variance explained (63-73%), but the manuscript reports neither cross-validation, stability across the two plants, nor sensitivity of the emission alignment to the choice of k or to the (unspecified) binary emission threshold.
minor comments (1)
  1. [Abstract] The abstract refers to 'functional summaries' of the high-N2O archetype without indicating the underlying data or methods (e.g., which functional databases or inference tools were used).

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for their thoughtful review and constructive comments on our manuscript. We address each of the major comments below and indicate the revisions we will make to strengthen the presentation.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the claim that the archetypal state space 'aligned strongly' with binary N2O emission states is presented without any quantitative measure of concentration (e.g., proportion of high-emission samples near the vertex or distance statistics) or statistical test of the alignment.

    Authors: We agree that the abstract would benefit from explicit quantitative support for the alignment claim. The full manuscript presents this via figures showing sample clustering and trajectories, but we will revise the abstract to report specific metrics such as the proportion of high-emission samples near the relevant vertex and reference a supporting statistical assessment (e.g., a distance-based or permutation test) performed on the data. revision: yes

  2. Referee: [Abstract] Abstract: temperature is explicitly noted to further structure the same simplex, yet no regression, stratification, or partial-correlation analysis is described to evaluate whether the archetype-N2O association is independent of temperature or potentially mediated by seasonal forcing on both community and emissions.

    Authors: This is a fair point; while the manuscript notes temperature's structuring effect, it does not include formal tests of independence. We will add a partial-correlation analysis (archetype weights vs. N2O emissions, controlling for temperature) and report the results in the revised manuscript to clarify the relationship. revision: yes

  3. Referee: [Abstract] Abstract: the number of archetypes is fixed at three on the basis of variance explained (63-73%), but the manuscript reports neither cross-validation, stability across the two plants, nor sensitivity of the emission alignment to the choice of k or to the (unspecified) binary emission threshold.

    Authors: The choice of k=3 follows the standard elbow criterion in variance explained for archetypal analysis, and the manuscript already demonstrates consistent patterns across both plants. To strengthen the claim, we will incorporate cross-validation, sensitivity analyses for alternative k values, and robustness checks with respect to the emission threshold in the methods and results of the revision. revision: yes

Circularity Check

0 steps flagged

No significant circularity; derivation is self-contained

full rationale

Archetypal analysis is applied unsupervised to genus-level microbiome profiles alone (no emission labels used in training), producing a simplex state space that is then inspected post-hoc for alignment with binary N2O states. The central claim is an observed correlation after the fact, not a reduction of any equation or parameter to a fitted input from the same emissions data. No self-citations, uniqueness theorems, or ansatzes from prior author work are invoked as load-bearing steps. The method is standard unsupervised dimensionality reduction followed by external correlation, which is independently verifiable and does not reduce to its inputs by construction.

Axiom & Free-Parameter Ledger

1 free parameters · 2 axioms · 0 invented entities

The claim rests on the mathematical validity of archetypal analysis for convex representation of compositional data and the assumption that the two Swiss plants are representative of broader WRRF behavior; no new entities are postulated.

free parameters (1)
  • Number of archetypes = 3
    Fixed at three to capture most explainable variation (63-73%); choice is data-driven but not derived from first principles.
axioms (2)
  • standard math Archetypal analysis yields interpretable extreme profiles whose convex combinations accurately summarize high-dimensional community data.
    Core modeling assumption invoked when reducing genus-level profiles to a simplex state space.
  • domain assumption Binary N2O emission states derived from continuous metrics are meaningful for alignment testing.
    Used to evaluate post-training clustering without being part of the AA training.

pith-pipeline@v0.9.1-grok · 5857 in / 1446 out tokens · 32071 ms · 2026-06-27T01:56:07.532493+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

46 extracted references · 45 canonical work pages

  1. [1]

    Linking Seasonal

    Gruber, Wenzel and Niederdorfer, Robert and Ringwald, J. Linking Seasonal. Water Research X , volume =. doi:10.1016/j.wroa.2021.100098 , urldate =

    work page doi:10.1016/j.wroa.2021.100098 2021

  2. [2]

    and Rudkj

    Dueholm, Morten Kam Dahl and Andersen, Kasper Skytte and Korntved, Anne-Kirstine C. and Rudkj. Nature Communications , volume =. doi:10.1038/s41467-024-49641-y , urldate =

    work page doi:10.1038/s41467-024-49641-y

  3. [3]

    IPCC Guidelines for National Greenhouse Gas Inventories , pages=

    Volume 5, Chapter 6 Wastewater treatment and discharge , author=. IPCC Guidelines for National Greenhouse Gas Inventories , pages=. 2006 , publisher=

    2006

  4. [4]

    Archetypal

    Cutler, Adele and Breiman, Leo , year = 1994, month = nov, journal =. Archetypal. doi:10.2307/1269949 , urldate =. 1269949 , eprinttype =

    work page doi:10.2307/1269949 1994

  5. [5]

    Alcacer, Aleix and Epifanio, Irene and Mair, Sebastian and M. A. doi:10.48550/arXiv.2504.12392 , urldate =. arXiv , keywords =:2504.12392 , primaryclass =

    work page doi:10.48550/arxiv.2504.12392

  6. [6]

    Ravishankara, A. R. and Daniel, John S. and Portmann, Robert W. , year = 2009, month = oct, journal =. Nitrous. doi:10.1126/science.1176985 , urldate =

    work page doi:10.1126/science.1176985 2009

  7. [7]

    and Massara, T.M

    Vasilaki, V. and Massara, T.M. and Stanchev, P. and Fatone, F. and Katsou, E. , year = 2019, month = sep, journal =. A Decade of Nitrous Oxide (. doi:10.1016/j.watres.2019.04.022 , urldate =

    work page doi:10.1016/j.watres.2019.04.022 2019

  8. [8]

    Water Science and Technology , volume =

    Methane and Nitrous Oxide Emissions from Municipal Wastewater Treatment -- Results from a Long-Term Study , author =. Water Science and Technology , volume =. doi:10.2166/wst.2013.109 , urldate =

    work page doi:10.2166/wst.2013.109 2013

  9. [9]

    and Van Voorthuizen, Ellen M

    Daelman, Matthijs R.J. and Van Voorthuizen, Ellen M. and Van Dongen, Udo G.J.M. and Volcke, Eveline I.P. and Van Loosdrecht, Mark C.M. , year = 2015, month = dec, journal =. Seasonal and Diurnal Variability of. doi:10.1016/j.scitotenv.2015.06.122 , urldate =

    work page doi:10.1016/j.scitotenv.2015.06.122 2015

  10. [10]

    doi:10.1016/j.scitotenv.2019.134157 , urldate =

    Gruber, Wenzel and Villez, Kris and Kipf, Marco and Wunderlin, Pascal and Siegrist, Hansruedi and Vogt, Liliane and Joss, Adriano , year = 2020, month = jan, journal =. doi:10.1016/j.scitotenv.2019.134157 , urldate =

    work page doi:10.1016/j.scitotenv.2019.134157 2020

  11. [11]

    Mechanisms of

    Wunderlin, Pascal and Mohn, Joachim and Joss, Adriano and Emmenegger, Lukas and Siegrist, Hansruedi , year = 2012, month = mar, journal =. Mechanisms of. doi:10.1016/j.watres.2011.11.080 , urldate =

    work page doi:10.1016/j.watres.2011.11.080 2012

  12. [12]

    Water Research , volume =

    Mitigating Nitrous Oxide Emissions at a Full-Scale Wastewater Treatment Plant , author =. Water Research , volume =. doi:10.1016/j.watres.2020.116196 , urldate =

    work page doi:10.1016/j.watres.2020.116196 2020

  13. [13]

    Genomics and

    Hallin, Sara and Philippot, Laurent and L. Genomics and. Trends in Microbiology , volume =. doi:10.1016/j.tim.2017.07.003 , urldate =

    work page doi:10.1016/j.tim.2017.07.003 2017

  14. [14]

    and Mitrovic, Ivan and Zeyer, Kerstin and Vogel, Michael and Von K

    Gruber, Wenzel and Magyar, Paul M. and Mitrovic, Ivan and Zeyer, Kerstin and Vogel, Michael and Von K. Tracing. Water Research X , volume =. doi:10.1016/j.wroa.2022.100130 , urldate =

    work page doi:10.1016/j.wroa.2022.100130 2022

  15. [15]

    doi:10.2166/9781789060461 , urldate =

    Quantification and. doi:10.2166/9781789060461 , urldate =

    work page doi:10.2166/9781789060461

  16. [16]

    Nature Sustainability , volume =

    Oversimplification and Misestimation of Nitrous Oxide Emissions from Wastewater Treatment Plants , author =. Nature Sustainability , volume =. doi:10.1038/s41893-024-01420-9 , urldate =

    work page doi:10.1038/s41893-024-01420-9

  17. [17]

    Water Research , volume =

    Exploring the Microbial Influence on Seasonal Nitrous Oxide Concentration in a Full-Scale Wastewater Treatment Plant Using Metagenome Assembled Genomes , author =. Water Research , volume =. doi:10.1016/j.watres.2022.118563 , urldate =

    work page doi:10.1016/j.watres.2022.118563 2022

  18. [18]

    Roothans, Nina and Pabst, Martin and Van Diemen, Menno and Herrera Mexicano, Claudia and Zandvoort, Marcel and Abeel, Thomas and Van Loosdrecht, Mark C. M. and Laureni, Michele , year = 2025, month = may, journal =. Long-Term Multi-Meta-Omics Resolves the Ecophysiological Controls of Seasonal. doi:10.1038/s44221-025-00430-x , urldate =

    work page doi:10.1038/s44221-025-00430-x 2025

  19. [19]

    doi:10.3389/fbioe.2023.1247711 , urldate =

    Xie, Yawen and Jiang, Cancan and Kuai, Benhai and Xu, Shengjun and Zhuang, Xuliang , year = 2023, month = nov, journal =. doi:10.3389/fbioe.2023.1247711 , urldate =

    work page doi:10.3389/fbioe.2023.1247711 2023

  20. [20]

    Organic Carbon Determines Nitrous Oxide Consumption Activity of Clade

    Qi, Chuang and Zhou, Yiwen and Suenaga, Toshikazu and Oba, Kohei and Lu, Jilai and Wang, Guoxiang and Zhang, Limin and Yoon, Sukhwan and Terada, Akihiko , year = 2022, month = feb, journal =. Organic Carbon Determines Nitrous Oxide Consumption Activity of Clade. doi:10.1016/j.watres.2021.117910 , urldate =

    work page doi:10.1016/j.watres.2021.117910 2022

  21. [21]

    Unraveling the Genetic Potential of Nitrous Oxide Reduction in Wastewater Treatment: Insights from Metagenome-Assembled Genomes , shorttitle =

    Schacksen, Patrick Skov and Nielsen, Jeppe Lund , editor =. Unraveling the Genetic Potential of Nitrous Oxide Reduction in Wastewater Treatment: Insights from Metagenome-Assembled Genomes , shorttitle =. Applied and Environmental Microbiology , volume =. doi:10.1128/aem.02177-23 , urldate =

    work page doi:10.1128/aem.02177-23

  22. [22]

    Selective Enrichment of High-Affinity Clade

    Laureni, Michele and. Selective Enrichment of High-Affinity Clade. ISME Communications , volume =. doi:10.1093/ismeco/ycaf022 , urldate =

    work page doi:10.1093/ismeco/ycaf022

  23. [23]

    and Van Lier, Jules B

    Seshan, Siddharth and Poinapen, Johann and Zandvoort, Marcel H. and Van Lier, Jules B. and Kapelan, Zoran , year = 2025, month = jan, journal =. Forecasting Nitrous Oxide Emissions from a Full-Scale Wastewater Treatment Plant Using. doi:10.1016/j.watres.2024.122754 , urldate =

    work page doi:10.1016/j.watres.2024.122754 2025

  24. [24]

    Chemosphere , volume =

    Linking Nitrous Oxide Emissions to Population Dynamics of Nitrifying and Denitrifying Prokaryotes in Four Full-Scale Wastewater Treatment Plants , author =. Chemosphere , volume =. doi:10.1016/j.chemosphere.2018.02.102 , urldate =

    work page doi:10.1016/j.chemosphere.2018.02.102 2018

  25. [25]

    and Galinha, C.F

    Vieira, A. and Galinha, C.F. and Oehmen, A. and Carvalho, G. , year = 2019, month = feb, journal =. The Link between Nitrous Oxide Emissions, Microbial Community Profile and Function from Three Full-Scale. doi:10.1016/j.scitotenv.2018.10.132 , urldate =

    work page doi:10.1016/j.scitotenv.2018.10.132 2019

  26. [26]

    Environmental Science and Pollution Research , volume =

    Nitrous Oxide Emissions and Microbial Communities Variation in Low Dissolved Oxygen and Low Carbon-to-Nitrogen Ratio Anoxic--Oxic Wastewater Treatment Plant , author =. Environmental Science and Pollution Research , volume =. doi:10.1007/s11356-024-33749-1 , urldate =

    work page doi:10.1007/s11356-024-33749-1

  27. [27]

    Nitrous Oxide Emission in a Laboratory Anoxic-Oxic Process at Different Influent

    Guo, Jingbo and Cong, Qiwei and Zhang, Jun and Zhang, Lanhe and Meng, Lingwei and Liu, Mingwei and Ma, Fang , year = 2021, month = may, journal =. Nitrous Oxide Emission in a Laboratory Anoxic-Oxic Process at Different Influent. doi:10.1016/j.biortech.2021.124844 , urldate =

    work page doi:10.1016/j.biortech.2021.124844 2021

  28. [28]

    Environmental Research , volume =

    Shift in Activated Sludge Microbiomes Associated with Nitrite Accumulation and High Nitrous Oxide Emissions , author =. Environmental Research , volume =. doi:10.1016/j.envres.2025.121591 , urldate =

    work page doi:10.1016/j.envres.2025.121591 2025

  29. [29]

    Identification of

    Kim, Daehyun D and Han, Heejoo and Yun, Taeho and Song, Min Joon and Terada, Akihiko and Laureni, Michele and Yoon, Sukhwan , year = 2022, month = sep, journal =. Identification of. doi:10.1038/s41396-022-01260-5 , urldate =

    work page doi:10.1038/s41396-022-01260-5 2022

  30. [30]

    and Park, Doyoung and Yoon, Hyun and Yun, Taeho and Song, Min Joon and Yoon, Sukhwan , year = 2020, month = oct, journal =

    Kim, Daehyun D. and Park, Doyoung and Yoon, Hyun and Yun, Taeho and Song, Min Joon and Yoon, Sukhwan , year = 2020, month = oct, journal =. Quantification of. doi:10.1016/j.watres.2020.116261 , urldate =

    work page doi:10.1016/j.watres.2020.116261 2020

  31. [31]

    Statistical Analysis and Data Mining: The ASA Data Science Journal , volume =

    Archetypal Analysis for Data-driven Prototype Identification , author =. Statistical Analysis and Data Mining: The ASA Data Science Journal , volume =. doi:10.1002/sam.11325 , urldate =

    work page doi:10.1002/sam.11325

  32. [32]

    Thomas , year = 2023, month = aug, journal =

    Hes, Cecilia and Jagoe, R. Thomas , year = 2023, month = aug, journal =. Gut Microbiome and Nutrition-Related Predictors of Response to Immunotherapy in Cancer: Making Sense of the Puzzle , shorttitle =. doi:10.1038/s44276-023-00008-8 , urldate =

    work page doi:10.1038/s44276-023-00008-8 2023

  33. [33]

    Microbiome , volume =

    Functional Archetypes in the Human Gut Microbiome Reveal Metabolic Diversity, Stability, and Influence Disease-Associated Signatures , author =. Microbiome , volume =. doi:10.1186/s40168-025-02240-5 , urldate =

    work page doi:10.1186/s40168-025-02240-5

  34. [34]

    Journal of Hazardous Materials , volume =

    Short- and Long-Term Effects of Temperature on Partial Nitrification in a Sequencing Batch Reactor Treating Domestic Wastewater , author =. Journal of Hazardous Materials , volume =. doi:10.1016/j.jhazmat.2010.03.027 , urldate =

    work page doi:10.1016/j.jhazmat.2010.03.027 2010

  35. [35]

    doi:10.1007/s00253-015-6742-7 , urldate =

    Poh, Leong Soon and Jiang, Xie and Zhang, Zhongbo and Liu, Yu and Ng, Wun Jern and Zhou, Yan , year = 2015, month = nov, journal =. doi:10.1007/s00253-015-6742-7 , urldate =

    work page doi:10.1007/s00253-015-6742-7 2015

  36. [36]

    The Impact of Temperature and Dissolved Oxygen (

    Wang, Jiawei and Yang, Hong and Liu, Xuyan and Wang, Jiawei and Chang, Jiang , year = 2020, journal =. The Impact of Temperature and Dissolved Oxygen (. doi:10.1039/D0RA05908K , urldate =

    work page doi:10.1039/d0ra05908k 2020

  37. [37]

    Nitrite Oxidizing Bacteria (

    Yao, Qian and Peng, Dang-Cong , year = 2017, month = dec, journal =. Nitrite Oxidizing Bacteria (. doi:10.1186/s13568-017-0328-y , urldate =

    work page doi:10.1186/s13568-017-0328-y 2017

  38. [38]

    Philosophical Transactions of the Royal Society B: Biological Sciences , volume =

    Nitrous Oxide Emissions from Wastewater Treatment Processes , author =. Philosophical Transactions of the Royal Society B: Biological Sciences , volume =. doi:10.1098/rstb.2011.0317 , urldate =

    work page doi:10.1098/rstb.2011.0317 2011

  39. [39]

    Learning

    Keller, Sebastian Mathias and Samarin, Maxim and Arend Torres, Fabricio and Wieser, Mario and Roth, Volker , year = 2021, month = apr, journal =. Learning. doi:10.1007/s11263-020-01390-3 , urldate =

    work page doi:10.1007/s11263-020-01390-3 2021

  40. [40]

    The Effect of Temperature Shifts on

    Bao, Zhiyuan and. The Effect of Temperature Shifts on. Chemosphere , volume =. doi:10.1016/j.chemosphere.2018.08.090 , urldate =

    work page doi:10.1016/j.chemosphere.2018.08.090 2018

  41. [41]

    Biarchetype

    Alcacer, Aleix and Epifanio, Irene and. Biarchetype. IEEE Transactions on Pattern Analysis and Machine Intelligence , volume =. doi:10.1109/TPAMI.2024.3400730 , urldate =

    work page doi:10.1109/tpami.2024.3400730 2024

  42. [42]

    Inferring Biological Tasks Using

    Hart, Yuval and Sheftel, Hila and Hausser, Jean and Szekely, Pablo and. Inferring Biological Tasks Using. Nature Methods , volume =. doi:10.1038/nmeth.3254 , urldate =

    work page doi:10.1038/nmeth.3254

  43. [43]

    Towards an Online Mitigation Strategy for

    Bellandi, Giacomo and Weijers, Stefan and Gori, Riccardo and Nopens, Ingmar , year = 2020, month = may, journal =. Towards an Online Mitigation Strategy for. doi:10.1016/j.jenvman.2020.110219 , urldate =

    work page doi:10.1016/j.jenvman.2020.110219 2020

  44. [44]

    and Conca, V

    Vasilaki, V. and Conca, V. and Frison, N. and Eusebi, A.L. and Fatone, F. and Katsou, E. , year = 2020, month = jul, journal =. A Knowledge Discovery Framework to Predict the. doi:10.1016/j.watres.2020.115799 , urldate =

    work page doi:10.1016/j.watres.2020.115799 2020

  45. [45]

    Pattern Recognition of Operational States Leading to

    Froemelt, Andreas and Zueger, Leon and Von Kaenel, Luzia and Braun, Daniel and Gruber, Wenzel , year = 2025, month = dec, journal =. Pattern Recognition of Operational States Leading to. doi:10.1016/j.wroa.2025.100336 , urldate =

    work page doi:10.1016/j.wroa.2025.100336 2025

  46. [46]

    and Mohn, Joachim and Joss, Adriano and Froemelt, Andreas , year = 2026, month = may, journal =

    Strubbe, Laurence and Keck, Hannes and Magyar, Paul M. and Mohn, Joachim and Joss, Adriano and Froemelt, Andreas , year = 2026, month = may, journal =. Activating Specific. doi:10.1016/j.watres.2026.125580 , urldate =

    work page doi:10.1016/j.watres.2026.125580 2026