Predicting power plant emissions using public data and machine learning
Literature Information
Jiajun Gu, Jeffrey A. Sward, K. Max Zhang
Accurately predicting emissions from electric generating units using only publicly available information is an important but challenging task. It provides a critical link in evaluating the environmental impact of energy transitions in the power sector, makes it possible to engage stakeholders in electricity product cost modeling and electricity markets without accessing proprietary data, and serves as an auditing tool to detect anomalies in self-reported emissions data. However, the absence of proprietary data also limits the prediction accuracy. In this paper, we adopted two novel and effective strategies to overcome this challenge. First, we utilized not only the emission monitoring data (such as the Continuous Emission Monitoring System (CEMS) data) as previous studies did but also a variety of auxiliary datasets in the public domain such as the EPA Field Audit Checklist Tool (FACT). Second, we employed machine learning techniques (Extreme gradient boosting (XGBoost) and neural networks (NN)) to take advantage of the large amount of public data available. We evaluated the effectiveness of our strategies by predicting NOx, SO2, and CO2 emission rates for all thermal electric generating units in New York State (NYS). Two models were developed: a full model to take a full inventory of public information and a reduced model for use in data-limited scenarios based on unit-level features that could be derived from a simplified power systems economic dispatch model. The models performed well for NOx emission rates overall compared to the previous results, achieving R2 values over 0.9 for both the full and reduced models. XGBoost and NN were shown to outperform the Linear Regression (LR) model consistently and significantly, which was employed previously to estimate unit-level emissions, especially in reduced models with a limited number of features available. The predictions of SO2 and CO2 emission rates showed strong overall predictive performance as well. We recommend stricter enforcement of the data reporting procedure, providing emission control operational information, and obtaining related data from multiple sources in the public domain as key steps to further improve the emission predictions.
Related Literature
The interaction of n-nonyl-β-d-glucopyranoside and sodium dodecyl sulfate with DMPC and DMPG monolayers studied by infrared reflection absorption spectroscopy
Annette Meister, Andreas Kerth, Alfred Blume
DOI: 10.1039/B410761F
Water dissociation at MgO sub-monolayers on silver: a periodic model study
DOI: 10.1039/B700526A
On the theory of complex-forming chemical reactions: effect of parity conservation on the polarization of differential cross sections
L. Bonnet, P. Larrégaray, J.-C. Rayez
DOI: 10.1039/B700906B
Photoinduced oxidation of [Mn(L)3]2+ and [Mn2O2(L)4]3+ (L = 2,2′-bipyridine and 4,4′-dimethyl-2,2′-bipyridine) with the [Ru(bpy)3]2+/-aryl diazonium salt system
Carole Baffert, Stéphane Dumas, Jérôme Chauvin, Jean-Claude Leprêtre, Marie-Noëlle Collomb, Alain Deronzier
DOI: 10.1039/B411365A
Electronic relaxation dynamics in DNA and RNA bases studied by time-resolved photoelectron spectroscopy
Susanne Ullrich, Thomas Schultz, Marek Z. Zgierski, Albert Stolow
DOI: 10.1039/B316324E
Direct quantum dynamics using variational multi-configuration Gaussian wavepackets. Implementation details and test case
B. Lasorne, M. A. Robb, G. A. Worth
DOI: 10.1039/B700297A
Predicting the reactivity of ambidentate nucleophiles and electrophiles using a single, general-purpose, reactivity indicator
DOI: 10.1039/B700960G
Endohedral clusterfullerenes—playing with cluster and cage sizes
Lothar Dunsch, Shangfeng Yang
DOI: 10.1039/B704143H
Allylic hydrogen abstraction II. H-abstraction from 1,4 type polyalkenes as a model for free radical trapping by polyunsaturated fatty acids (PUFAs)‡
Milan Szori, Tamas Abou-Abdo, Christa Fittschen, Bela Viskolcz
DOI: 10.1039/B613048H
You might also like
What is Ethyl 3-cyclohexylpropanoate (CAS: 10094-36-7)?
Ethyl 3-cyclohexylpropanoate is a clear, colorless to light yellow liquid with a...
How should waste containing 2-(Hydroxymethyl)-5-(methoxycarbonyl)-6-methyl-4-(2-nitrophenyl)nicotinic acid (CAS: 34783-31-8) be handled?
Waste containing 2-(Hydroxymethyl)-5-(methoxycarbonyl)-6-methyl-4-(2-nitrophenyl...
How should waste containing 2,4,6-Tris(pentafluoroethyl)-1,3,5-triazine (CAS: 858-46-8) be handled?
Waste containing 2,4,6-Tris(pentafluoroethyl)-1,3,5-triazine (CAS: 858-46-8) sho...
What precautions should be taken when handling Chloroac-nle-oh (CAS: 56787-36-1)?
When handling Chloroac-nle-oh (CAS: 56787-36-1), it is essential to wear appropr...
What industries use Ethyl 6-phenylimidazo[2,1-b][1,3]thiazole-3-carboxylate (CAS: 752244-05-6)?
Ethyl 6-phenylimidazo[2,1-b][1,3]thiazole-3-carboxylate is primarily used in the...
Are there alternatives to alpha-(2-Bromophenyl)benzylamine (CAS: 55095-15-3) in synthesis?
Alternatives to alpha-(2-Bromophenyl)benzylamine (CAS: 55095-15-3) in synthesis ...
How should waste containing 2-Chloro-5-methoxypyridine (CAS: 139585-48-1) be handled?
Waste containing 2-Chloro-5-methoxypyridine (CAS: 139585-48-1) should be managed...
What industries use 1-(4-Methoxyphenyl)-2,5-dimethyl-1H-pyrrole (CAS: 5044-27-9)?
1-(4-Methoxyphenyl)-2,5-dimethyl-1H-pyrrole (CAS: 5044-27-9) is used in various ...
Are there alternatives to 3-Bromo-5-(N-Boc)aminomethylisoxazole (CAS: 903131-45-3) in synthesis?
There are alternative reagents and compounds that can be used in the synthesis o...
What is Tungsten(IV) oxide (CAS: 12036-22-5)?
Tungsten(IV) oxide, also known as tungsten dioxide, is a chemical compound with ...















