Application of Machine Learning for Anaerobic Digestion

ChoiSujin

출간작으로『ApplicationofMachineLearningforAnaerobicDigestion』등이있다.

TABLEOFCONTENTS

PREFACEii
TABLEOFCONTENTSiii
Chapter1.AnaerobicDigestion1
1.1Introduction1
1.2BiochemistryandMicrobiology3
1.2.1Hydrolysis-3
1.2.2Acidogenesis-4
1.2.3Acetogenesis4
1.2.4Methanogenesis5
1.3ProcessControlofAnaerobicDigestion6

Chapter2.StatisticalMethodsinAnaerobicDigestion11
2.1Multipleregression11
2.1.1Fundamentalsofmultipleregression12
2.1.2Responsesurfacemethodology15
2.1.2.1DesignofexperimentsinAD16
2.1.2.2Centralcompositedesign17
2.1.2.3Fullfactorialandfractionalfactorialdesigns22
2.1.3ApplicationofRSMinADprocesses26
2.2Multivariateanalysistechniques29
2.2.1OverviewofmultivariatemethodsinAD29
2.2.2Principlecomponentanalysis(PCA)32
2.2.2.1Mathematicalfoundation33
2.2.2.2ApplicationofPCAinAD34
2.2.2.3InterpretationofPCAresults35
2.2.2.4Interpretationofkeyparameters36
2.2.3Redundancyanalysis-39
2.2.3.1Linkingenvironmentalparameterstomicrobialcommunities41
2.2.4PrincipleCoordinateanalysis48
2.2.4.1Applicationsinsamplecomparisonandclustering51
2.2.5Non-metricmultidimensionalscaling58
2.2.5.1Conceptandapplicationinmicrobialcommunityanalysis61
2.2.6CanonicalCorrespondenceAnalysis68
2.2.6.1Correlatingmicrobialcommunitiesandprocessperformance71

Chapter3.KineticsofMicrobialGrowthandSubstrateUtilization78
3.1GeneralconceptsofbiokineticsinAD78
3.1.1Definitionandimportance82
3.1.2Microbialgrowthcurve83
3.2ImportanceofBiokineticsinADProcessContro89
3.3FundamentalKineticModelsinAD96
3.3.1MonodModel97
3.3.2HaldaneModel99
3.3.3ContoisModel100
3.3.4Lotka-VolterraModel102
3.3.4.1Casestudies:Interactionmodeling108
3.4Fundamentalbiokineticequations111
3.4.1Massbalanceequationdevelopment113
3.4.2Analyticalsolutions115
3.4.2.1Solutionforbatchreactors115
3.4.2.2SolutionforCSTRs117
3.4.3Numericalsolutions119
3.4.3.14thorderRunge-KuttaMethod119
3.4.3.2Solutionforbatchreactors121
3.4.3.3SolutionforCSTRs-123
3.5Kineticparameterestimation125
3.6Applicationsofbiokineticmodelinginperformanceprediction128

Chapter4.ArtificialIntelligence(AI)-basedmethodsinAnaerobicDigestion131
4.1GeneralIntroductiontoAI131
4.1.1BasicsofAI-134
4.1.2AIApproachinAnaerobicDigestion136
4.1.3CommonAITasksinAnaerobicDigestionsystems138
4.1.3.1Prediction140
4.1.3.2Classification141
4.1.3.3Clustering141
4.1.3.4AnomalyDetection142
4.2DescriptionofModelArchitectures144
4.2.1MachineLearningAlgorithms145
4.2.1.1LinearRegression147
4.2.1.2SupportVectorMachine(SVM)151
4.2.1.3NaïeBayes156
4.2.1.4DecisionTrees161
4.2.1.5EnsembleLearningModels166
4.2.2NeuralNetworkArchitectures174
4.2.2.1Multi-layerPerceptrons(MLP)175
4.2.2.2ConvolutionalNeuralNetworks(CNN)182
4.2.2.3RecurrentNeuralNetworks(RNN)194
4.2.2.4Transformer206
4.3TrainingandValidationofModels219
4.3.1DataSplitting222
4.3.2LearningObjectives223
4.3.3ModelOptimization-225
4.3.4ValidationandEvaluationofModels229

Chapter5.ApplicationofAIinAnaerobicDigestionresearch234
5.1Physico-ChemicalData234
5.1.1ReactorConfiguration235
5.1.2SubstrateCharacteristics236
5.1.3EffluentCharacteristics238
5.1.4GasPhaseData239
5.1.5ApplicationsinAIModeling241
5.2QualitativeandQuantitativeMicrobialData243
5.2.1QualitativeMicrobialData244
5.2.1.1CommunityStructure244
5.2.1.2DiversityIndices245
5.2.1.3ApplicationsinAIModeling246
5.2.2QuantitativeMicrobialData-248
5.2.2.1MicrobialQuantificationusingqPCR249
5.2.2.2ApplicationsinAIModeling249
5.2.3IntegrationofQualitativeandQuantitativeData250
5.3ImageData252
5.3.1SpectroscopyImage254
5.3.1.1ApplicationinInfluentAnalysis254
5.3.1.2ApplicationinEffluentAnalysis254
5.3.1.3ApplicationsinAIModeling255
5.3.2MicroscopyImage257
5.3.2.1BiofilmandGranuleAnalysis258
5.3.2.2MicrobialCommunityImaging258
5.3.2.3ApplicationsinAIModeling259
5.4Time-seriesData-261
5.4.1CharacteristicsofTime-seriesData262
5.4.2PreprocessingRequirementsforAIApplications263
5.4.3ApplicationsinAIModeling-264
REFERENCES266