Microbial fuel cells (MFCs) are promising bioelectrochemical systems for converting organic matter into electrical energy, but their practical relevance depends on both functional performance and sustainability-oriented viability. This study evaluated the bioelectrochemical behavior of double-chamber MFCs inoculated with kefir, comparing graphene and graphite anodes under fed-batch operation. A total of 33 MFC series were monitored longitudinally through voltage, current, power output, substrate consumption, and oxidation-reduction potential. Under the LED-connected closed-circuit configuration used here, kefir-inoculated reactors exhibited a reproducible electrical response together with near-complete substrate depletion. These findings support kefir as a workable mixed inoculum for comparative reactor operation under the tested conditions, although direct extracellular electron transfer and exclusive microbial causation of the measured signal were not demonstrated. Graphene showed higher early and mean electrical performance than graphite, particularly in power-related metrics, although this advantage decreased over time and did not result in a categorical separation of final batch-level outcomes. In contrast, substrate consumption remained highly similar between anode materials, indicating that the main material effect was expressed in electrochemical translation rather than in overall substrate conversion. Taxonomic profiling supported the presence of a metabolically complementary consortium dominated by lactic acid bacteria, acetic acid bacteria, Gram-negative bacteria, and yeasts. Deterministic sensitivity analysis and Monte Carlo-based LCA/TEA screening further showed that the most sustainable scenario was not necessarily the one with the highest electrical response, highlighting the importance of integrating performance, material burden, and uncertainty in MFC assessment.

Monthly cane supply anticipation is critical for harvest scheduling, mill intake coordination, transport allocation, labor planning, and maintenance organization in vertically integrated sugarcane agroindustrial systems. This study developed an interpretable monthly decision support framework using twelve years of original institutional records from Compañía Azucarera Valdez S.A., Milagro, Guayas, coastal Ecuador, covering January 2007 to December 2018. The primary endpoint was one-month-ahead monthly cane tonnage, predicted from variables available at the current monthly time point to avoid look-ahead bias. Complementary diagnostic layers were used to characterize recurrent operational states and to interpret monthly energy-saving behavior. A chronological validation design was applied, with 2007–2015 used for model training and 2016–2018 used for independent testing. The full linear and LASSO models achieved the strongest test performance, with R² values of 0.916 and 0.915 and mean absolute percentage errors near 5%, outperforming random forest and ANN/MLP benchmarks. The area-only baseline was weaker, while the no-area model retained predictive capacity, indicating that harvested area was important but insufficient to explain monthly cane tonnage. PCA and k-means clustering identified four recurrent operational states related to production scale, stress, crop quality, and energy performance conditions. Monthly energy saving showed ceiling-constrained behavior near 40% and was therefore interpreted as a diagnostic indicator rather than a robust forecasting target. Overall, the framework supports transparent monthly planning by combining leakage-aware forecasting, operational-state interpretation, and conservative energy performance diagnostics.

Monthly cane-supply anticipation is critical for harvest scheduling, mill-intake coordination, transport allocation, labor planning, and maintenance organization in vertically integrated sugarcane agroindustrial systems. This study developed an interpretable monthly decision-support framework using twelve years of original institutional records from Compañía Azucarera Valdez S.A., Milagro, Guayas, coastal Ecuador, covering January 2007 to December 2018. The primary endpoint was one-month-ahead monthly cane tonnage, predicted from variables available at the current monthly time point to avoid look-ahead bias. Complementary diagnostic layers were used to characterize recurrent operational states and to interpret monthly energy-saving behavior. A chronological validation design was applied, with 2007–2015 used for model training and 2016–2018 used for independent testing. The full linear and LASSO models achieved the strongest test performance, with R² values of 0.916 and 0.915 and mean absolute percentage errors near 5%, outperforming random forest and ANN/MLP benchmarks. The area-only baseline was weaker, while the no-area model retained predictive capacity, indicating that harvested area was important but insufficient to explain monthly cane tonnage. PCA and k-means clustering identified four recurrent operational states related to production scale, stress, crop quality, and energy-performance conditions. Monthly energy saving showed ceiling-constrained behavior near 40% and was therefore interpreted as a diagnostic indicator rather than a robust forecasting target. Overall, the framework supports transparent monthly planning by combining leakage-aware forecasting, operational-state interpretation, and conservative energy-performance diagnostics.