Nitrous oxide (N2O) emissions from nitrogen-fertilized agricultural soils represent a critical yet poorly quantified component of the greenhouse gas balance in Peruvian coffee systems. This study developed and compared machine learning (ML) and multiple linear regression models for predicting N2O fluxes from coffee soils under five contrasting nitrogen fertilization treatments in Chirinos, San Ignacio, Cajamarca, Peru. A dataset of 135 observations (n = 135), integrating edaphic and meteorological variables, was assembled from field measurements using static closed chambers and gas chromatography. Models were trained on 80% of the data and validated on the remaining 20% using holdout cross-validation. Random Tree and Random Forest consistently outperformed traditional regression approaches, both achieving R2 = 0.94, whereas REPTree reached R2 = 0.44, and multiple linear regression showed limited predictive capacity (R2 ≤ 0.50). The best-performing model, Random Tree Model IV, achieved a mean absolute error (MAE) of 14.79 mg N2O–N m−2 d−1. Variable importance analysis identified nitrogen source, soil temperature, relative air humidity, porosity, and water-filled pore space as the primary drivers of emission variability, consistent with established microbial mechanisms of nitrification and denitrification. These findings demonstrate that ML-based approaches substantially outperform conventional linear methods for modeling the nonlinear dynamics of N2O in coffee soils and provide actionable evidence for nitrogen management strategies that prioritize organic sources as mitigation options in high-rainfall environments. Limitations include the one-month evaluation period and the absence of microbiological variables, which future studies should address to improve model transferability.
5 January 2026 in Clean Energy Science and Technology
Ignorance of the sustainability of coffee systems compromises the continuity of productive activities by weakening their economic viability, environmental integrity and social cohesion over time, which is why it is essential to carry out diagnoses. This study aimed to assess the sustainability level of coffee farms associated with the Cooperativa Agraria Cafetalera La Prosperidad de Chirinos. From January to March 2024, data were collected from 60 farms out of a population of 788. The analysis was based on nine criteria: six environmental (soil quality, crop health, solid waste and effluent management, integrated pest and disease management, ecological knowledge, and agricultural system), two economic (agricultural economy and food sovereignty), and one social (social aspects). To identify groups of farmers with homogeneous characteristics, a cluster analysis was performed and the level of sustainability of each group was determined by calculating overall averages, represented through Amoeba charts. Results identified two farm types farms in group 1 showed less sustainability than group 2, mainly due to unfavorable conditions related to soil quality. Consequently, it is recommended to to implement cover crops, live barriers, infiltration ditches, contour planting, and productive diversification for food security are recommended. This study provides a scientific diagnosis of sustainability levels on coffee farms and offers practical options for improving sustainability.
Romerillo (Retrophyllum rospigliosii), a vulnerable conifer native to the cloud forests of Cajamarca, Peru, persists in small remnants at high altitudes in San Ignacio province, where its integration into agroforestry systems may support both conservation and sustainable production. This study aimed to model the growth of R. rospigliosii associated with coffee (Coffea arabica L.) using diameter and height as indicators. Field data were collected over 18 months in two experimental plots and the study analyzed 329 individuals selected from 600 initially planted, with monthly monitoring to evaluate early growth and survival dynamics. The data were analyzed with nonlinear mathematical models, including Schumacher, Chapman–Richards, and Weibull, with model selection based on goodness-of-fit and prediction statistics such as R2, AIC, and BIC. Results showed that Schumacher provided the best performance for height (R2 = 0.98, AIC = 27,978.54), while Weibull (R2 = 0.80, AIC = 27,204.63) and Chapman–Richards (R2 = 0.80, AIC = 27,207.97) also yielded consistent estimates. For diameter, Schumacher was the most accurate (R2 = 0.92, AIC = 2627.87). Survival analysis revealed significant differences between plots (p = 0.011), with higher survival at 1820 m (87.8% at 18 months) compared to 1540 m (77.3%). These findings indicate that the Schumacher model is most suitable for growth estimation, while altitude plays a critical role in survival, underscoring its importance in establishing R. rospigliosii within coffee-based agroforestry systems.
12 October 2026 in ISPRS Open Journal of Photogrammetry and Remote Sensing
Global warming, driven by rising greenhouse gas (GHG) concentrations, has agriculture as a major source of emissions. In coffee plantations, low sampling frequency and the absence of diurnal baselines introduce bias in emission estimates. The objective of this research was to estimate diurnal CO₂, N₂O, and CH₄ emissions from unfertilized coffee soils using recurrent neural networks (RNN). Gas fluxes were measured with a closed dynamic chamber (CDC) at 20-minute intervals between 8:00 and 18:00 over 22 days. For the estimation of GHG emissions, climatic data measured through a meteorological station were used, in addition to environmental parameters incorporated in the CDC. Five RNN models composed of two hidden layers of 20, 25, and 50 neurons were developed, trained, and validated for each GHG. Results indicate that N₂O contributed most to total emissions (734,689 ppm CO₂-eq), with CO₂ (237,579 ppm CO₂-eq) and CH₄ (215,426 ppm CO₂-eq) contributing less. Model performance was strong, with R² values of 0.98 (CO₂), 0.96 (N₂O), and 0.94 (CH₄). It is concluded that the RNNs proved to be reliable models for predicting GHG emissions in unfertilized coffee soils, with this study presenting a replicable framework with the potential to improve temporal estimation and reduce uncertainty in GHG inventories.
11 March 2026 in Remote Sensing Applications: Society and Environment