Bud Rot (BR) is the most significant phytosanitary threat to oil palm cultivation in Colombia. Early detection is essential for effective curative management, but current methods for detecting BR in adult palms are subjective and unreliable. This research aimed to develop an integrated system for digital field monitoring and image analysis, testing two detection methods: computer-assisted detection and automatic detection using artificial intelligence (AI). Monthly monitoring was conducted over a 12-month period (January–December 2022) on 672 African oil palms (Elaeis guineensis), 15 years old and susceptible to BR. Disease monitoring focused on the incidence, cumulative incidence, and labor performance based on the number and spatial distribution of palms detected with BR, with or without the use of the device proposed. Results showed that automatic detection using AI had low effectiveness (17.1%), identifying only a small portion of actual cases. In contrast, computer-assisted detection significantly improved accuracy, reaching 78.6% during peak months and reducing detection time by up to two months compared to traditional methods, although, its maximum performance point only reached 4.7 ha/wage. The implementation of digital monitoring provides crucial technological support by considerably improving the effectiveness of early detection in BR curative management. Future advancements in AI-based detection are expected to further improve the efficiency and functionality of this approach.

The production of oil palm is a major agricultural activity in Colombia. Lethal wilt (LW) of the oil palm is one of the most devastating diseases in the Eastern zone of the country. Several epidemiological models used in epidemic analyses assume that there is a constant area where the host will become diseased at the end of the epidemic (maximum incidence of disease = 100%). Based on the analysis of three different epidemics, we demonstrated the error in the application of the model that best fits the observed data when the maximum incidence of the disease (Kmax) is below the assumed. We assessed the fit of the monomolecular, logistic, and Gompertz models at different final incidence values of the disease including the maximum observed (y1 + 0.1). We analyzed the data with linear regression and residuals variance and distribution. We measured the relative quality level of fit of the model for each Kmax by determining coefficients (R2) and the Akaike and Bayesian information criteria (AIC & BIC). The monomolecular model showed a tendency to increase the level of adjustment when Kmax assumed values were close to 1 while the logistic and Gompertz models remained stable regardless of the evaluated Kmax values. The consequences of assuming a Kmax with values equal to 1 reflected not only the erroneous estimation of parameters such as y0 and r but also gave rise to a misinterpretation of the temporal behavior of the epidemic. La producción de palma de aceite es muy importante en Colombia. La marchitez letal de la palma de aceite es una enfermedad muy limitante en la zona oriental colombiana. Algunos modelos empleados en el análisis de estas epidemias se basan en el supuesto de que existe un área constante donde el hospedante llega a enfermarse al final de ellas (incidencia máxima de la enfermedad = 100 %). El análisis de tres epidemias diferentes demostró el error que se comete en la aplicación del modelo que mejor se ajusta a los datos observados, con una máxima incidencia de la enfermedad (Kmax) por debajo de la asumida. El ajuste de los modelos monomolecular, logístico y Gompertz se hizo con diferentes incidencias, incluida la máxima observada (y1 + 0,1). Los datos se sometieron a análisis de regresión lineal y de varianza y distribución de los residuales. La calidad del ajuste se midió mediante los coeficientes de determinación (R2), el análisis de regresión lineal y los criterios de información Akaike (CIA) y bayesiano (CIB). Se evidenció la sensibilidad del modelo monomolecular cuando la incidencia máxima de la enfermedad se asumió por encima del valor real, contrario a lo observado en los modelos logístico y Gompertz, cuyos valores se mantuvieron estables independientemente del aumento de la Kmax evaluada. Las consecuencias de asumir una Kmax con valores igual a 1 no solamente se reflejan en la estimación errónea de parámetros como el y0 y el r, sino que también conduce a una mala interpretación del comportamiento de la epidemia.

La gotera u ojo de gallo es una enfermedad de épocas húmedas o con lluvias frecuentes; sin embargo, su manejo preventivo se inicia desde la época seca o con lluvias scasas y se continua durante todo el ciclo de producción y de cosecha.

Basal Stem Rot (BSR), caused by Ganoderma spp., is one of the most important emerging diseases of oil palm in Colombia and is so far restricted to only two producing areas in the country. However, despite the controls established to prevent its spread to new areas, containment has not been possible. This study aimed to understand BSR’s propagation mechanisms and related environmental conditions by measuring Ganoderma basidiospores’ concentrations at various heights using four 7-day Burkard volumetric samplers in a heavily affected plantation. Meteorological data, including solar radiation, temperature, humidity, precipitation, and wind speed, were also recorded. Analysis revealed higher basidiospore concentrations below 4 m, peaking at 02:00 h, with increased levels towards the study’s end. Spore concentrations were not directly influenced by temperature, humidity, or precipitation, but showed higher releases during drier periods. A significant correlation was found between wind speed and spore concentration, particularly below 1.5 m/s, though higher speeds might aid long-distance pathogen spread. This study highlights the complexity of BSR propagation and the need for continued monitoring and research to manage its impact on Colombia’s oil palm industry.

CLR (Hemileia vastatrix) is the disease with the greatest economic and social impact on coffee production in the world, causing losses of up to 50% of productivity in susceptible varieties without proper and timely management. The department of Huila is the current largest producer with approximately 19% of production, going from 136,000 ha planted in 2012 with 61% in susceptible varieties, to about 150,000 ha in 2020 and 30% in susceptible varieties, mainly in the southern area of ??the department, indicating the advancement of the department's coffee sector. However, there is still an important area under threat from coffee rust, which must be controlled and reduced. The objective of this work was to validate the chemical management strategy for rust in commercial crops of the susceptible variety Caturra in the south of the department of Huila (Colombia). The evaluation was carried out in two commercial crops of var. Caturra at two altitudes at 1.410 and 1.280 m, where each batch was divided into three plots to monitor the blooms and the percentage of incidence of the disease from 2016 to 2018. The validation criteria consisted of: fixed calendars (CC1), adjustment of the main flowering (CC2), farmer (CA3), and finally without disease control (SC4). The incidence in critical periods was above 30% of the level of economic damage, directly accompanying the physiology of production. The criteria (CC1-CC2) and with the use of the recommended fungicide showed a lower incidence (AUDPC) compared to the other criteria evaluated, presenting a positive effect on the control of the disease, allowing a retention of foliage and delaying the curve of the disease reducing to 30% the incidence in critical periods. In addition, the risk of Colombian coffee growing has increased in recent years, especially due to the climatic variability that generates advances or delays in the peaks of the disease and generating reductions in the incubation periods.

Con el objetivo de mejorar las evaluaciones cuantitativas de severidad de roya del cafeto en las diferentes investigaciones de Cenicafé sobre biología, epidemiología, resistencia genética y manejo integral de roya en Colombia, y para fortalecer el monitoreo de la enfermedad en variedades susceptibles y resistentes por parte del Servicio de Extensión de la FNC, asistentes técnicos y los caficultores, se desarrolló y validó un Diagrama de Área Estándar nuevo para la roya del cafeto en el campo, comparándolo con los diagramas existentes.