The use of non-crop plants to provide the resources that herbivorous crop pests’ natural enemies need is being increasingly incorporated into integrated pest management programs. We evaluated insect functional groups found on three refuges consisting of five different plant species each, planted next to a maize crop in Lima, Peru, to investigate which refuge favoured natural control of herbivores considered as pests of maize in Peru, and which refuge plant traits were more attractive to those desirable enemies. Insects occurring in all the plants, including the maize crop itself, were sampled weekly during the crop growing cycle, from February to June 2011. All individuals collected were identified and classified into three functional groups: herbivores, parasitoids, and predators. Refuges were compared based on their effectiveness in enhancing the populations of predator and parasitoid insects of the crop enemies. Refuges A and B were the most effective, showing the highest richness and abundance of both predators and parasitoids, including several insect species that are reported to attack the main insect pests of maize (Spodoptera frugiperda and Rhopalosiphum maidis), as well as other species that serve as alternative hosts of these natural enemies.

This study assessed the integration of Unmanned Aerial Vehicles (UAVs) and satellite images (Sentinel-1 and Sentinel-2) in advanced machine-learning techniques to monitor the ABV of quinoa crops (Jacha Grano variety) across the Bolivian Altiplano. The proposed method follows a two-step procedure. First, UAV RGB images were used in photogrammetric and deep-learning (Convolutional Neural Networks-CNN) models to estimate reference quinoa ABVs at a 10 m spatial resolution from the crop canopy 3D model and classification, respectively. Secondly, several spectral and polarization/texture indices derived from Sentinel-2 and -1 images were integrated into three decision-tree-based machine-learning models (Random Forest-RF, Gradient Boosting-GB, eXtreme Gradient Boosting-XGB), and one CNN-based machine-learning model to estimate ABV. Additionally, a Stacking Model (STM) build on top of the three decision-tree-based models was considered for comparison. Model evaluation was also performed in a two-step approach. First, a 10-fold cross-validation strategy was used to highlight ABV sensitivity to Sentinel-2 and Sentinel-1 alone and in combination. Secondly, a Leave-One-Plot-Out Cross-Validation (LOPOCV) strategy was used to avoid autocorrelation between the training and evaluation dataset and therefore provided more insight into ABV mapping potential. The results showed that the combination of Sentinel-1 and Sentinel-2 features in the CNN model achieved the best predictive performance with R² and RMSE values of 0.64 and 0.39 m³ ∙ 100 m⁻², respectively. These findings highlight the potential of integrating multi-source information in advanced artificial intelligence algorithms for quinoa ABV monitoring, offering new insights toward the identification of sustainable practices across remote regions with complex socio-economic contexts.

El Gorgojo de los Andes es la principal plaga que ocasiona y causa daño en el cultivo de papa generando bajos rendimientos en su producción agrícola. En Bolivia, la papa es la principal fuente de ingresos económicos para los agricultores de los valles y del altiplano. La investigación se desarrolló para incorporar y demostrar la importancia y efectividad de los componentes amigables con la naturaleza como el uso del Eco-insecticida BioMax para el control eficiente del Gorgojo de los Andes. La metodología se basa en las siguientes etapas: siembra de cultivo de papa, recolección de gorgos adultos en campo, separando los gorgojos por grupos, aplicación de tres dosis del Eco-insecticida Biomax, formas de aplicación (directa y indirecta). Las evaluaciones se realizaron en laboratorio, se implementó ensayo en envases con 15 Gorgojos de la especie Premnotrypes spp. por tratamiento (5 U.E. por tratamiento) y 4 repeticiones por tratamiento, las cuales se asperjo con Biomax a dosis de 1,0; 1,5; 2,0 lt/ha del Eco-insecticida Biomax, el efecto del Biomax se evaluó el 14,17,21 y 28 días., después de su aplicación, registrando el número de insectos muertos. La eficiencia se determinó mediante la fórmula de Henderson y Tillton (% Mortalidad = 100 x [1 - (Ta x Cb) / (Tb x Ca)]), en base al numero de insectos vivos en las dosis de Biomax y en el Testigo. Según los resultados en laboratorio, la eficiencia del control de Biomas en los gorgojos Adultos Premnotrypes spp., en cuanto a los resultados obtenidos: Aplicación del Eco-insecticida BioMax de diferentes dosis, donde el T3 (2lt/ha con aplicación directa) llego a tener una eficiencia del 73,3% en los tres días después de la aplicación, lo cual en los T2 (1,5lt/ha con aplicación directa) y T1 (1lt/ha con aplicación directa) tuvieron menor eficiencia 53,3% y 43,3%. Mientras con la aplicación indirecta; los T4 (1lt/ha), T5 (1,5lt/ha) lograron tener una eficiencia baja 33,3%, 43,3% a los tres días de aplicación, lo cual el T6 (2lt/ha) logro tener una eficiencia 63,3% a los cuatro días de la aplicación del BioMax.