Manuela Ortega-Monsalve

The adoption of emerging information and communication technologies (ICTs) in agriculture can significantly boost productivity and crop sustainability, yet integration remains challenging due to multiple influencing factors. Existing literature is fragmented, with studies examining specific technologies, contexts, or factors in isolation, limiting a comprehensive understanding of adoption drivers, barriers, and impacts. This chapter presents a systematic literature review following PRISMA guidelines, addressing four research questions: (1) which variables are most relevant for adopting emerging agricultural technologies; (2) what are the main obstacles and challenges; (3) what are the main advantages and prospects; and (4) to what extent has information technology been applied, which tools have been used, and on what type of farm. A taxonomy is proposed to structure the analysis and classify the reviewed literature according to each research question. Results show that adoption is influenced by prior knowledge, educational level, access to credit, and government support. Key obstacles include high acquisition costs, limited knowledge, inadequate infrastructure, institutional restrictions, and youth migration from rural areas. Benefits identified include greater productive efficiency, predictive analytics for decision-making, and the generation of new projects. The most widely used technologies are crop yield mapping, precision irrigation systems, soil and environmental sensors, and precision seeding. The review suggests future research should account for external factors such as market trends, political changes, and global events. Notably, most technological advances and institutional support remain concentrated in developed countries. Overall, this review offers an integrative overview of the key characteristics, advantages, and limitations of emerging technology adoption in agriculture.

Practical nesting materials compatible with conventional farrowing crates remain limited. This study evaluated the effects of long paper strips on periparturient sow behavior, farrowing duration, and early piglet outcomes. Ninety multiparous sows were assigned to long paper strips (LP; n = 45) or no nesting material (CON; n = 45). Sows in the LP group received 300 g of paper strips 18 h before the expected date of farrowing. Behavioral observations were conducted on a subset of 14 sows. Prepartum, LP sows performed more nest-building behavior (P < 0.01) and less redirected nest-building behavior (P < 0.01). During farrowing, LP sows performed less nest-building behavior (P = 0.04), and postpartum, they spent more time nursing (P = 0.04). Farrowing duration was 51 min shorter in LP sows (P = 0.01). Piglet outcomes were not affected. These findings suggest that a small quantity of long paper strips can support nest-building behavior in crated sows and may represent a low-volume material option for conventional farrowing systems.

Las relaciones establecidas entre los distintos nutrientes del suelo pueden influir en las condiciones para el crecimiento de las plantas. En este caso, las producciones ganaderas dependen de la biomasa de los pastos para alimentar a los animales. Se determinó la relación del carbono orgánico (CO), el nitrógeno (N) total empleando modelos aditivos generalizados (GAM), por medio de análisis de regresiones y suavizados, en suelos dedicados a la producción bovina de leche, carne y doble propósito. En los modelos se incluyeron nutrientes presentes en el suelo y efectos del ambiente, como la ubicación. Se determinó el ajuste por medio de la Devianza y el R2 y se realizó un análisis descriptivo de las relaciones entre las variables incluidas en los modelos y sus distribuciones espaciales para cada tipo de producción. El CO se relacionó con variables del suelo, como la densidad aparente (DA), la capacidad de intercambio catiónico (CIC), el pH y el N total. El N total se relacionó con el CO, la arcilla, el potasio y el zinc. Los suelos del Norte y Oriente del departamento, dedicados a la producción de leche, registraron niveles más altos de CO, mientras que el Urabá y Magdalena Medio, dedicados a la producción de carne, registraron valores más bajos. Para el N total, el Norte y el Oriente presentaron valores menores que las demás regiones. Las relaciones carbono/nitrógeno (C/N) encontradas para las producciones no presentaron una relación lineal; los valores de dichas relaciones dependen del contenido de N total del suelo.

Spectroscopy is a promising technique for determining nutrients in grasses and may be a valuable tool for future research. This chapter reviews research carried out in recent years, focusing on determining the quality of grasses using spectroscopy techniques, specifically, spectrophotometry. The chemical methods used to determine the nutritional quality of grasses produce chemical residues, are time-consuming, and are costly to use when analyzing large crop extensions. Spectroscopy is a non-destructive technique that can establish the nutritional quality of grass easily and accurately. This chapter aims to describe the techniques focused on the use of spectroscopy and machine learning models to predict and determine the quality of grasses. A bibliographic review was conducted and recent research articles were selected that showed spectroscopic techniques applied to grasses. Different methods and results focusing on the quality of the grasses were compiled. In general, this review showed that the most commonly used spectroscopic method is near-infrared analysis. Spectroscopy is a very effective tool that opens the way to new types of technologies that can be applied to obtain results in determining the quality of pastures, leaving behind the use of traditional methods that represent higher costs and disadvantages compared to traditional methods based on precision agriculture.

Organic carbon and total nitrogen are essential nutrients for plant growth. The presence of these nutrients at acceptable levels can create an optimal environment for the development of crops of interest. The application of spectroscopic techniques and the use of machine learning algorithms have made it possible to calibrate models capable of predicting the number of elements present in the soil. One of these techniques is hyperspectral imaging, which captures portions of the electromagnetic spectrum where the materials present in the soil can be differentiated due to the vibrations of chemical bonds. The objective of this research is to use statistical models to predict OC and N in soils from hyperspectral images. Transformations were applied to spectral and chemical data and the models used were Random Forest (RF) and Support Vector Machine (SVM). To select the best model, the values of the coefficient of determination (R²), root mean square error of prediction (RMSEP), and the ratio of performance to deviation (RPD) were considered. For OC, the values found for the RF model were an R² of 0.87, an RMSEP of 0.10, and an RPD of 6.74; the SVM model presented an R² of 0.92, an RMSEP of 0.20, and an RPD of 3.56. For the variable N, the values found for the RF model were an R² of 0.79, an RMSEP of 0.03, and an RPD of 5.44; for the SVM model, they were an R² of 0.87, an RMSEP of 0.08, and an RPD of 2.76. The RF model showed a better fit for both variables. The SVM model also produced acceptable results. The results show that machine learning models are a good alternative for analysing soil‐related variables.

El objetivo del estudio fue ajustar las curvas de crecimiento de cuatro Urochloas mediante un modelo matemático que permita la comparación entre ellas. Se tuvieron en cuenta las variables de altura (cm), temperatura (°C), precipitación (mm) y edad del pasto (días). El crecimiento de cada especie se analizó en el software estadístico R-Project. Se ajustaron los datos de crecimiento de las especies con el uso del modelo cuadrático yt = β0 +β1 t -β3 t2, con coeficientes de determinación (>0.9) y un valor de p<0.001. Como resultado, Urochloa brizantha cv Piatá presentó un R² = 0.9859 y fue la especie más influenciada positivamente en su crecimiento por el efecto de la edad (días), seguido por U. decumbens, U. mutica y U. brizantha cv Toledo, esta última con el menor ajuste. La precipitación influyó en la tasa de crecimiento de la U. mutica mientras que la temperatura no tuvo influencia en el crecimiento de las especies. Las curvas se ajustaron a modelos cuadráticos, lo que indica que su crecimiento puede compararse y predecirse a lo largo del tiempo, lo que facilita su manejo y óptimo aprovechamiento.