Remote sensing is essential in precision agriculture as this approach provides high-resolution information on the soil’s physical and chemical parameters for detailed decision making. Globally, technologies such as remote sensing and machine learning are increasingly being used to infer these parameters. This study evaluates soil fertility changes and compares them with previous fertilization inputs using high-resolution multispectral imagery and in situ measurements. A UAV-captured image was used to predict the spatial distribution of soil parameters, generating fourteen spectral indices and a digital surface model (DSM) from 103 soil plots across 49.83 hectares. Machine learning algorithms, including classification and regression trees (CART) and random forest (RF), modeled the soil parameters (N-ppm, P-ppm, K-ppm, OM%, and EC-mS/m). The RF model outperformed others, with R² values of 72% for N, 83% for P, 87% for K, 85% for OM, and 70% for EC in 2023. Significant spatiotemporal variations were observed between 2022 and 2023, including an increase in P (14.87 ppm) and a reduction in EC (−0.954 mS/m). High-resolution UAV imagery combined with machine learning proved highly effective for monitoring soil fertility. This approach, tailored to the Peruvian Andes, integrates spectral indices and field-collected data, offering innovative tools to optimize fertilization practices, address soil management challenges, and merge modern technology with traditional methods for sustainable agricultural practices.

Precision agriculture aims to improve crop management using advanced analytical tools. In this context, the objective of this study is to develop an innovative predictive model to estimate the yield and morphological quality, such as the circularity and length–width ratio of potato tubers, based on phenotypic characteristics of plants and data captured through spectral cameras equipped on UAVs. For this purpose, the experiment was carried out at the Santa Ana Experimental Station in the central Peruvian Andes, where advanced potato clones were planted in December 2023 under three levels of fertilization. Random Forest, XGBoost, and Support Vector Machine models were used to predict yield and quality parameters, such as circularity and the length–width ratio. The results showed that Random Forest and XGBoost achieved high accuracy in yield prediction (R² > 0.74). In contrast, the prediction of morphological quality was less accurate, with Random Forest standing out as the most reliable model (R² = 0.55 for circularity). Spectral data significantly improved the predictive capacity compared to agronomic data alone. We conclude that integrating spectral indices and multitemporal data into predictive models improved the accuracy in estimating yield and certain morphological traits, offering key opportunities to optimize agricultural management.

Accurate and timely estimation of oat biomass is crucial for the development of sustainable and efficient agricultural practices. This research focused on estimating and predicting forage oat biomass using UAV and agronomic variables. A Matrice 300 equipped with a multispectral camera was used for 14 flights, capturing 21 spectral indices per flight. Concurrently, agronomic data were collected at six stages synchronized with UAV flights. Data analysis involved correlations and Principal Component Analysis (PCA) to identify significant variables. Predictive models for forage biomass were developed using various machine learning techniques: linear regression, Random Forests (RFs), Support Vector Machines (SVMs), and Neural Networks (NNs). The Random Forest model showed the best performance, with a coefficient of determination R² of 0.52 on the test set, followed by Support Vector Machines with an R² of 0.50. Differences in root mean square error (RMSE) and mean absolute error (MAE) among the models highlighted variations in prediction accuracy. This study underscores the effectiveness of photogrammetry, UAV, and machine learning in estimating forage biomass, demonstrating that the proposed approach can provide relatively accurate estimations for this purpose.

Tarwi (Lupinus mutabilis S.) is a legume native to the Andes, recognized for its high nutritional value, which gives it great potential in food security programs. Therefore, understanding and advancing the conservation of its morphological diversity is essential. In this study, 140 accessions from the national germplasm collection of the National Institute of Agrarian Innovation of Peru were evaluated, along with two cultivars ("INIA 445 Masacanchino" and "Andenes 90"). A traditional agro-morphological characterization was conducted using 16 quantitative and 40 qualitative descriptors, complemented by phenological data obtained from time series of reflectance indices generated by Unmanned Aerial Vehicles (UAVs). Additionally, a principal component analysis (PCA) was applied to select the most relevant variables, and a clustering analysis along with a dendrogram was developed to classify the accessions. The results revealed significant differences between groups (p < 0.05) in terms of inflorescence length, number of pods on the main axis, number of primary branches, and yield per plant. Likewise, the morphological groups exhibited variations in phenophases derived from the Normalized Difference Vegetation Index (NDVI). Four morphological groups were identified: group 3 (G3) showed the highest growth rate followed by a decline, while group 4 (G4) stood out for its highest initial growth rate. Furthermore, the observed homogeneous phenological conditions indicated that groups 1 (G1) and 4 (G4) matured earlier, making them promising candidates for selection. These findings demonstrate the wide genetic variability of tarwi, which can be exploited in breeding programs for the development of new cultivars. Thus, the study highlights the importance of morphological characterization in understanding the variability of an understudied crop such as tarwi, contributing to conservation and promoting its protection and sustainability.