Search

[Display omitted] • Thermally pretreated harvest residues and manure were anaerobically co-digested. • Four machine learning methods were tested for biogas and methane yield prediction. • Recursive Feature Elimination was the optimal feature selection approach. • R2 for biogas and methane yield prediction was up to 0.820 and 0.823, respectively. • An ensemble machine learning produced stable accuracy regardless of input datasets. This study aimed to clarify the statistical accuracy assessment approaches used in recent biogas prediction studies using state-of-the-art ensemble machine learning approach according to 10-fold cross-validation in 100 repetitions. Three thermally pretreated harvest residue types (maize stover, sunflower stalk and soybean straw) and manure were anaerobically co-digested, measuring biogas and methane yield alongside eight thermal preprocessing and biomass covariates. These were the inputs to an ensemble machine learning approach for biogas and methane yield prediction, employing three feature selection approaches. The Support Vector Machine prediction with the Recursive Feature Elimination resulted in the highest prediction accuracy, achieving the coefficient of determination of 0.820 and 0.823 for biogas and methane yield prediction, respectively. This study demonstrated an extreme dependency of prediction accuracy to input dataset properties, which could only be mitigated with ensemble machine learning and strongly suggested that the split-sample approach, often used in previous studies, should be avoided. [ABSTRACT FROM AUTHOR]

• Soil C:N is an indicator of soil quality for sustainable organic farming. • K-means algorithm was implemented for the determination of soil C:N deficiency zones. • Ordinary kriging outperformed lognormal kriging and inverse distance weighted. • A total of 45.6% of the study area was determined as unsuitable for organic farming. Soil carbon-to-nitrogen ratio (C:N) represents an indicator of soil quality and fertility, having a major impact on agricultural land management for organic farming. Determination of soil C:N suitability zones is a necessary procedure in the process, enabling effective land management. A total of 72 soil samples at two soil layers at 0–10 cm and 20–30 cm were used in the study, evenly distributed in the Osijek-Baranja County in eastern Croatia. Ordinary kriging (OK) and Lognormal kriging (LK) using linear, Gaussian and spherical mathematical models, alongside Inverse distance weighted (IDW) were evaluated for the spatial prediction of soil C:N. Inner accuracy representing retention of input sample values in the interpolation results and outer accuracy representing a prediction accuracy at unknown locations were used to determine optimal interpolation parameters. K-means unsupervised classification algorithm was used for the objective determination of soil C:N suitability zones in five classes specified by the Food and Agriculture Organization (FAO). IDW resulted in the highest inner accuracy, while OK with the Gaussian model produced the highest outer accuracy with the average R2 = 0.7908 and NRMSE = 0.0544. Contrary to the previous research, higher mean soil C:N results in a lower soil layer of 20–30 cm with 13.41, compared to 12.03 at 0–10 cm soil layer. The highest soil C:N suitability was determined in only 4.8% of the study area, with the suitability index of 18.44. Meanwhile, the two largest classes were marginally suitable and currently unsuitable class, covering 35.5% and 27.7% of the study area, respectively. These results indicated a necessity for the adjustment of agricultural land management practices to enable sustainable organic farming. [ABSTRACT FROM AUTHOR]