The rapid population growth has driven the demand for more food, fiber, energy, and water, which is associated to an increase in the need to use natural resources in a more sustainable way. The use of precision agriculture machinery and equipment since the 1990s has provided important productive gains and maximized the use of agricultural inputs. The growing connectivity in the rural environment, in addition to its greater integration with data from sensor systems, remote sensors, equipment, and smartphones have paved the way for new concepts from the so-called Agriculture 4.0 or Digital Agriculture. This article presents the results of a survey carried out with 504 Brazilian farmers about the digital technologies in use, as well as current and future applications, perceived benefits, and challenges. The questionnaire was prepared, organized, and made available to the public through the online platform LimeSurvey and was available from 17 April to 2 June 2020. The primary data obtained for each question previously defined were consolidated and analyzed statistically. The results indicate that 84% of the interviewed farmers use at least one digital technology in their production system that differs according to technological complexity level. The main perceived benefit refers to the perception of increased productivity and the main challenges are the acquisition costs of machines, equipment, software, and connectivity. It is also noteworthy that 95% of farmers would like to learn more about new technologies to strengthen the agricultural development in their properties.

This paper presents a framework based on machine learning algorithms to predict nutrient content in leaf hyperspectral measurements. This is the first approach to evaluate macro- and micronutrient content with both machine learning and reflectance/first-derivative data. For this, citrus-leaves collected at a Valencia-orange orchard were used. Their spectral data was measured with a Fieldspec ASD FieldSpec^® HandHeld 2 spectroradiometer and the surface reflectance and first-derivative spectra from the spectral range of 380 to 1020 nm (640 spectral bands) was evaluated. A total of 320 spectral signatures were collected, and the leaf-nutrient content (N, P, K, Mg, S, Cu, Fe, Mn, and Zn) was associated with them. For this, 204,800 (320 × 640) combinations were used. The following machine learning algorithms were used in this framework: k-Nearest Neighbor (kNN), Lasso Regression, Ridge Regression, Support Vector Machine (SVM), Artificial Neural Network (ANN), Decision Tree (DT), and Random Forest (RF). The training methods were assessed based on Cross-Validation and Leave-One-Out. The Relief-F metric of the algorithms’ prediction was used to determine the most contributive wavelength or spectral region associated with each nutrient. This approach was able to return, with high predictions (R²), nutrients like N (0.912), Mg (0.832), Cu (0.861), Mn (0.898), and Zn (0.855), and, to a lesser extent, P (0.771), K (0.763), and S (0.727). These accuracies were obtained with different algorithms, but RF was the most suitable to model most of them. The results indicate that, for the Valencia-orange leaves, surface reflectance data is more suitable to predict macronutrients, while first-derivative spectra is better linked to micronutrients. A final contribution of this study is the identification of the wavelengths responsible for contributing to these predictions.

Monitoring biomass of forages in experimental plots and livestock farms is a time-consuming, expensive, and biased task. Thus, non-destructive, accurate, precise, and quick phenotyping strategies for biomass yield are needed. To promote high-throughput phenotyping in forages, we propose and evaluate the use of deep learning-based methods and UAV (Unmanned Aerial Vehicle)-based RGB images to estimate the value of biomass yield by different genotypes of the forage grass species Panicum maximum Jacq. Experiments were conducted in the Brazilian Cerrado with 110 genotypes with three replications, totaling 330 plots. Two regression models based on Convolutional Neural Networks (CNNs) named AlexNet and ResNet18 were evaluated, and compared to VGGNet—adopted in previous work in the same thematic for other grass species. The predictions returned by the models reached a correlation of 0.88 and a mean absolute error of 12.98% using AlexNet considering pre-training and data augmentation. This proposal may contribute to forage biomass estimation in breeding populations and livestock areas, as well as to reduce the labor in the field.

Tropical forests are often located in difficult-to-access areas, which make high-quality forest structure information difficult and expensive to obtain by traditional field-based approaches. LiDAR (acronym for Light Detection And Ranging) data have been used throughout the world to produce time-efficient and wall-to-wall structural parameter estimates for monitoring in native and commercial forests. In this study, we compare products and aboveground biomass (AGB) estimations from LiDAR data acquired using an aircraft-borne system in 2015 and data collected by the unmanned aerial vehicle (UAV)-based GatorEye Unmanned Flying Laboratory in 2017 for ten forest inventory plots located in the Chico Mendes Extractive Reserve in Acre state, southwestern Brazilian Amazon. The LiDAR products were similar and comparable among the two platforms and sensors. Principal differences between derived products resulted from the GatorEye system flying lower and slower and having increased returns per second than the aircraft, resulting in a much higher point density overall (11.3 ± 1.8 vs. 381.2 ± 58 pts/m²). Differences in ground point density, however, were much smaller among the systems, due to the larger pulse area and increased number of returns per pulse of the aircraft system, with the GatorEye showing an approximately 50% higher ground point density (0.27 ± 0.09 vs. 0.42 ± 0.09). The LiDAR models produced by both sensors presented similar results for digital elevation models and estimated AGB. Our results validate the ability for UAV-borne LiDAR sensors to accurately quantify AGB in dense high-leaf-area tropical forests in the Amazon. We also highlight new possibilities using the dense point clouds of UAV-borne systems for analyses of detailed crown structure and leaf area density distribution of the forest interior.

Forage dry matter is the main source of nutrients in the diet of ruminant animals. Thus, this trait is evaluated in most forage breeding programs with the objective of increasing the yield. Novel solutions combining unmanned aerial vehicles (UAVs) and computer vision are crucial to increase the efficiency of forage breeding programs, to support high-throughput phenotyping (HTP), aiming to estimate parameters correlated to important traits. The main goal of this study was to propose a convolutional neural network (CNN) approach using UAV-RGB imagery to estimate dry matter yield traits in a guineagrass breeding program. For this, an experiment composed of 330 plots of full-sib families and checks conducted at Embrapa Beef Cattle, Brazil, was used. The image dataset was composed of images obtained with an RGB sensor embedded in a Phantom 4 PRO. The traits leaf dry matter yield (LDMY) and total dry matter yield (TDMY) were obtained by conventional agronomic methodology and considered as the ground-truth data. Different CNN architectures were analyzed, such as AlexNet, ResNeXt50, DarkNet53, and two networks proposed recently for related tasks named MaCNN and LF-CNN. Pretrained AlexNet and ResNeXt50 architectures were also studied. Ten-fold cross-validation was used for training and testing the model. Estimates of DMY traits by each CNN architecture were considered as new HTP traits to compare with real traits. Pearson correlation coefficient r between real and HTP traits ranged from 0.62 to 0.79 for LDMY and from 0.60 to 0.76 for TDMY; root square mean error (RSME) ranged from 286.24 to 366.93 kg·ha${}^{-1}$ for LDMY and from 413.07 to 506.56 kg·ha${}^{-1}$ for TDMY. All the CNNs generated heritable HTP traits, except LF-CNN for LDMY and AlexNet for TDMY. Genetic correlations between real and HTP traits were high but varied according to the CNN architecture. HTP trait from ResNeXt50 pretrained achieved the best results for indirect selection regardless of the dry matter trait. This demonstrates that CNNs with remote sensing data are highly promising for HTP for dry matter yield traits in forage breeding programs.