Prediction of composting maturity and identification of critical parameters for green waste compost using machine learning

Machine learning-based prediction of compost maturity and identification of key parameters during manure composting

Evaluating compost maturity, e.g. via manual seed germination index (GI) measurement, is both time-consuming and costly during composting. This study employed six machine learning methods, including random forest (RF), extra tree (ET), eXtreme gradient boosting, gradient boosting decision tree, back propagation neural network, and multilayer perceptron, to develop models for predicting GI during manure composting. RF and ET exhibited robust predictive performance for GI, achieving high coefficient of determination (R2) of 0.937 and 0.904, respectively, along with root mean squared error of 7.261 and 8.930. SHapley additive exPlanations identified the duration time of composting, total nitrogen, and electrical conductivity as the key features influencing GI. Validation with actual GI data further confirmed the effectiveness of RF and ET models in predicting GI. This study could facilitate optimizing manure composting strategies, enable efficient parameter regulation, reduce labor costs, assist in anomaly detection, and promote intelligent management in real-world composting practices.

Harnessing the potential of exogenous microbial agents: a comprehensive review on enhancing lignocellulose degradation in agricultural waste composting

Composting converts organic agricultural wastes into value-added products, yet the presence of significant non-biodegradable lignocelluloses hinders its efficiency. The introduction of various exogenous microbial agents has been shown to effectively addresses this challenge. In this context, basing on the microbial enzymatic mechanism for lignocellulose degradation, this paper synthesizes the latest research advancements and practical applications of exogenous microbial agents in agricultural waste composting. Given that the effectiveness of lignocellulose degradation is highly dependent on the waste's inherent characteristics, it is crucial to carefully consider the composition of fungi and bacteria, the dosage of microbial agents, and the composting process operation, tailored to the specific type of agricultural waste. Moreover, the combination of additives with exogenous microbial agents can further enhance the degradation of lignocelluloses and the humification of organic matters. Furthermore, insights into the future research and application trends of exogenous microbial agents in agricultural waste composting was prospected.

Producing agri-food derived composts from coffee husk as primary feedstock at different temperature conditions

There is a great global concern about agricultural wastes from food and feed crop processing that have significant environmental impacts. Composting is the most environmentally friendly, cost-effective, and efficient processes that can solve the problems of accumulation and toxicity of agricultural waste. The aim of this study is the detoxification of coffee husk by composting at two temperature conditions ("warm" and "cold"). In the greenhouse, the ambient temperature was changed day by day to mimic the situation of a spring to summer "warm" period (≈16-34 °C) and a spring "cold" period (≈7-20 °C) typical of central Italy. The coffee industry should accept the responsibility for the large amount of organic waste production, which presents toxicity and mass accumulation problems. Coffee husk as the main raw material is not used directly as bio-fertilizer in agriculture sector due to the leaching of phenolic compounds and high pH value. The brewing industry is famous for its mass production, and the brewer residues as a by-product have an extremely acidic pH that makes them an unsuitable material for direct composting, but the mixture of these materials can optimize pH. The addition of cow manure accelerates microbial activity and is a strategy to improve composting rate and maturity. The following mixtures were tested: coffee husk and brewer spent grains in a proportion of 2:1 (Compost 1), coffee husk and cow manure in a proportion of 4:1 (Compost 2), and coffee husk, brewer spent grain, and cow manure in a proportion of 5:3:2 (Compost 3). Quality and maturity of the final composts appeared to be affected by the ambient temperature conditions, which remarkably affected pH, C/N ratio, nutrient and trace elements availability, germination index, microbial biomass carbon, and FDA hydrolysis. Results showed that both sets of temperatures produced composts to be considered standard compost, but "warm" conditions compost showed greater maturity, while the composts produced under "cold" conditions were able to increase seed gemination.

Hyperthermophilic composting coupled with vermicomposting stimulates transformation of organic matter by altering bacterial community

Hyperthermophilic composting (HTC) has been proven to be an effective strategy to recycle organic wastes, while vermicomposting (VC) has been widely applied to produce humic fertilizer. The combination of HTC with VC (HVC) is expected to integrate the advantages of both. This study showed that HTC pre-fermentation provided plentiful substances such as dissolved organic matter (DOM) for the subsequent VC enriching humic acid (HA). Compared to thermophilic composting (TC), HVC significantly stimulated the degradation of organic matter (OM) and the production of N-rich HA, and incubated higher diversity of bacterial community. SHapley Additive exPlanations (SHAP), correlation network, Mantel test and PLS-LM model were constructed to identify the potential roles of the key bacterial groups contributing to OM transformation. Firmicutes (e.g., Bacillus and Tuberibacillus) dominant in HTC may mineralize and mobilize OM, providing affluent bioavailable nutrients as part of DOM for microbial metabolism and abundant precursors for HA formation in the further VC. Actinobacteriota (e.g., Microbacterium) and Bacteroidota (e.g., Flavobacterium and Parapedobacter) prominent in VC metabolized DOM, mineralized OM and produced HA probably by enhancing the metabolic activity involved in OM degradation and amino acid generation. However, when DOM was exhausted, some members especially Proteobacteria (e.g., Ochrobactrum, Devosia and Cellvibrio) would change their roles from promoter to inhibitor of mineralization and humification. Altering the nutrient bioavailability and the composition of bacterial community can regulate the mineralization, mobilization and humification of OM. Overall, this study provides new insights into the roles of bacteria participating in transforming organic wastes into HA-rich composts.

Optimizing the early-stage of composting process emissions - artificial intelligence primary tests

Although composting has many advantages in treating organic waste, many problems and challenges are still associated with emissions, like NH3, CO and H2S, as well as greenhouse gases such as CO2. One promising approach to enhancing composting conditions is using novel analytical methods based on artificial intelligence. To predict and optimize the emissions (CO, CO2, H2S, NH3) during the early-stage of composting process machine learning (ML) models were utilized. Data about emissions from laboratory composting with compost's biochar with different incubation (50, 60, 70 °C) and biochar doses (0, 3, 6, 9, 12, 15% dry mass) were used for ML models selections and training. ML models such as acritical neural network (ANN, Bayesian Regularized Neural Network; R2 accuracy CO:0.71, CO2:0.81, NH3:0.95, H2S:0.72) and decision tree (DT, RPART; R2 accuracy CO:0.69, CO2:0.80, NH3:0.93, H2S:0.65) have demonstrated satisfactory results. The ML models to predict CO and H2S during composting were demonstrated for the first time. Utilizing emission data to predict other noxious gases presents a cost-effective and expeditious alternative to the empirical analysis of compost properties.

Predicting maturity and identifying key factors in organic waste composting using machine learning models

The measurement of germination index (GI) in composting is a time-consuming and laborious process. This study employed four machine learning (ML) models, namely Random Forest (RF), Artificial Neural Network (ANN), Support Vector Regression (SVR), and Decision Tree (DT), to predict GI based on key composting parameters. The prediction results showed that the coefficient of determination (R2) for RF (>0.9) and ANN (>0.9) was higher than SVR (<0.6) and DT (<0.8), suggesting that RF and ANN displayed superior predictive performance for GI. The SHapley additive exPlanations value result indicated that composting time, temperature, and pH were the important features contributing to GI. Composting time was found to have the most significant impact on GI. Overall, RF and ANN were suggested as effective tools for predicting GI in composting. This study offers the reliable approach of accurately predicting GI in composting processes, thereby enabling intelligent composting practices.

Humification and fungal community succession during pig manure composting: Membrane covering and mature compost addition

The objective of this study was to elucidate the combined effect of a semi-permeable membrane (M) and mature compost (MC) on humification and fungal community succession in pig manure composting. Compared with the control, the concentrations of humic substances (HSs) increased by 44.54 % (M + 15 % MC) and 43.90 % (M). During the thermophilic phase, Aspergillus (67.26 %) was the dominant genus in the M + 15 % MC treatment. Membrane covering increased the relative abundance (RA) of other phyla (except for Ascomycetes and Basidiomycetes) on the 14th day and Basidiomycetes on the 80th day in M treatment. Humic acid, HSs were positively correlated with the RA of genera Myceliophthora, Kernia, and Mycothermus. Myceliophthora was the key genus in the M + 15 % MC treatment on the 80th day. The results showed that 15 % MC addition under membrane covering optimizes the quality of composting products.