[pt] O biogás é uma energia renovável com grande potencial de produção a partir de resíduos, incluindo resíduos alimentares. Nesse contexto, o presente trabalho apresenta o desenvolvimento de três modelos distintos usando Redes Neurais Artificiais (RNAs), com a capacidade de prever o volume acumulado de biogás, de metano e a concentração de CH4, respectivamente. Foi construído um banco de dados da literatura com variáveis do processo de biodigestão anaeróbia: tipo de biomassa, tipo de reator/alimentação, teor de sólido volátil, pH, taxa de carga orgânica, tempo de retenção hidráulica, temperatura e volume do reator. Para cada conjunto de modelos, foram desenvolvidas e testadas 24 RNAs utilizando a ferramenta computacional MATLAB. As RNAs foram avaliadas pela sua capacidade de estimação através do coeficiente de determinação (R2 ) e também através da soma do erro quadrático (SSE) obtidos. Após as etapas iniciais, as redes neurais foram usadas para criar superfícies de resposta, buscando regiões ideais para produção de biogás e metano. Contudo, um único modelo não atingiu a representatividade desejada, levando à segmentação dos dados por tipo de biomassa. As RNAs desenvolvidas demonstraram eficácia na estimação dos grupos usados para treinamento, teste e validação. A melhor rede alcançou R2 de 0,9969 para biogás, 0,9963 para metano e 0,9386 para a porcentagem de metano, com SSE de 0,1808, 0,1089 e 11,45, respectivamente. A estratégia de combinar variáveis do processo em superfícies de resposta revelou-se útil para identificar pontos ótimos no processo produtivo. / [en] Biogas is a renewable energy source with significant production potential from various waste materials, including food waste. In this context, this study presents the development of three distinct models using Artificial Neural Networks (ANNs), capable of predicting the cumulative volume of biogas, methane, and CH4 concentration, respectively. A literature-based database was constructed, including variables from anaerobic digestion processes: biomass type, reactor/feed type, volatile solid content, pH, organic loading rate, hydraulic retention time, temperature, and reactor volume. For each set of models, 24 ANNs were developed and tested using the MATLAB computational tool. The ANNs estimation capability was assessed using the coefficient of determination (R2) and the sum of squared errors (SSE). Following initial stages, neural networks were employed to create response surfaces, aiming to identify optimal regions for biogas and methane production. However, a single model failed to achieve the desired representativeness, leading to data segmentation based on biomass type. The developed ANNs demonstrated effectiveness in estimating the groups used for training, testing, and validation. The best network achieved R2 values of 0.9969 for biogas, 0.9963 for methane, and 0.9386 for methane percentage, with SSE values of 0.1808, 0.1089, and 11.45, respectively. The strategy of combining process variables in response surfaces proved valuable in identifying optimal points in the production process.

Behovet av bättre avfallshantering ökar ständigt då befolkningen ökar och jordbruket intensifieras. Avfallshanteringen idag är dåligt konstruerad för organiskt avfall i många länder då det hamnar på deponier som släpper ut växthusgaser till atmosfären vilket påverkar klimatet negativt. En möjlig lösning att implementera en metod som genererar en värdefull produkt så som fluglarvskompostering. Det är en organisk avfallsbehandlingsmetod som använder larver av den amerikanska vapenflugan som kan reducera mängden avfall. Avfallet omvandlas till larvernas biomassa som är proteinrik och kan användas som djurfoder. Behandlingsresterna kan användas som gödningsmedel eller producera biogas. Väldigt lite är känt gällande växthusgasutsläppen från fluglarvskompostering. Under nuvarande EU lagstiftning i produktionssammanhang så är flugan ett produktionsdjur, som inte tillåts att födas upp på matavfall innehållande animaliska biprodukter. Därför har vegetabiliskt matavfall undersökts i denna studie för att i produktionssammanhang kunna använda sig av fluglarvskompostering. De vegetabiliska avfallet som använts var apelsinskal och blomkål blandat med broccoli (i denna studie kallad blomkålsblandning). Vegetabiliskt avfall innehåller svåråtkomlig näring för larverna och för att de ska kunna tillgodose sig så mycket som möjligt gjordes förbehandlingar. Förbehandlingarna som utfördes var med svamp och med ammoniumlösning då dessa har visat sig spjälka upp svåråtkomlig näring. Matavfall är känt för att fungera bra i fluglarvskompostering och användes som referens. Utsläpp av växthusgaserna CO2, NH3, N2O och CH4 undersöktes genom användande av kammarteknik. Vid behandlingar av blomkålsblandningen förbättrade förbehandlingarna materialreduktionen endast lite, vilket var i genomsnitt 82 %, men den totala minskningen i detta substrat var större än för matavfall vars reduktion var 60 %. Reduktionen varierade mellan 38-86 % i behandlingarna av apelsinskal. Larvbehandlingen av matavfall resulterade i den högsta omvandlingskvoten. Båda vegetabiliska substraten förbehandlat med NH4+ hade höga utsläpp av NH3. Behandlingarna av blomkålsblandningen hade högre utsläpp av N2O men mindre än i konventionella avfallsbehandlingar som kompostering. De substrat som inte förbehandlats hade låga utsläpp av CH4, inklusive matavfallet jämfört med de förbehandlade substraten som var mindre än i aerobisk kompostering. När en behandlingsstrategi väljs för kompostering med fluglarver, för små gasutsläpp så bör svampförbehandlat substrat användas, medan substrat förbehandlat med NH4+ resulterar i högre materialreduktion. / The need for better waste management is increasing as the population increases and agriculture is intensified. Organic waste management today is poorly designed in many countries leading to waste ending up in landfills which results in more greenhouse gases being emitted to the atmosphere, contributing to the global climate change. A possible solution is to implement a method that generates a valuable product such as fly larvae composting, which is an organic waste treatment method that uses larvae of the black soldier fly that can reduce the amount of waste. The waste is converted to the larval biomass which is rich in protein and possible to use as animal feed. Treatment residues can be used as fertilizers or to produce biogas. Very little is known about greenhouse gas emissions from fly larvae composting. Under current EU legislation in production contexts, the fly is considered a production animal that is not allowed to be raised on food waste containing animal by-products. Therefore, in this study, vegetable waste was investigated in order to be able to use fly larvae composting in production contexts. The vegetable waste used was orange peels and cauliflower mixed with broccoli (in this study referred to as cauliflower mix). Vegetable waste contains nutrients which are hard to digest for larvae and in order to improve digestibility, pretreatments were performed. The pretreatments carried out were with fungus and ammonia solution, as these have been shown to make hardly bound nutrients available. Food waste is known to work well in fly larvae composting and was used as a reference. Emissions of greenhouse gases CO2, NH3, N2O and CH4 were measured using chamber technique. In the treatment of cauliflower mix, the pretreatment improved the material reduction only slightly, which was on average 82 % but the overall total reduction was greater than that for food waste which had a reduction at 60 %. The reduction ranged between 38-86 % among all of the treatments of orange peels. Larvae treatment on food waste resulted in the largest biomass conversion ratio. Both vegetable substrates pretreated with NH4+ had high emissions of NH3. The treatments of cauliflower mix had higher emissions of N2O but they were lower than what is generally expected in conventional waste treatments such as composting. The non-pretreated substrates had low emissions of CH4, including the food waste compared to the pretreated ones which nevertheless were lower than in aerobic composting. When selecting a treatment strategy for fly larvae composting, to achieve low gas emissions, fungus pretreated substrates should be used while substrates pretreated with NH4+ result in higher material reduction.