Under ideal conditions of nitrogen (N), maize (Zea mays L.) can grow to its full potential, reaching maximum plant height (PH). As a rapid and nondestructive approach, the analysis of unmanned aerial vehicles (UAV)-based imagery may be of assistance to estimate N and height. The main objective of this study is to present an approach to predict leaf nitrogen concentration (LNC, g kg−1) and PH (m) with machine learning techniques and UAV-based multispectral imagery in maize plants. An experiment with 11 maize cultivars under two rates of N fertilization was carried during the 2017/2018 and 2018/2019 crop seasons. The spectral vegetation indices (VI) normalized difference vegetation index (NDVI), normalized difference red-edge index (NDRE), green normalized difference vegetation (GNDVI), and the soil adjusted vegetation index (SAVI) were extracted from the images and, in a computational system, used alongside the spectral bands as input parameters for different machine learning models. A randomized 10-fold cross-validation strategy, with a total of 100 replicates, was used to evaluate the performance of 9 supervised machine learning (ML) models using the Pearson’s correlation coefficient (r), mean absolute error (MAE), coefficient of regression (R²), and root mean square error (RMSE) metrics. The results indicated that the random forest (RF) algorithm performed better, with r and RMSE, respectively, of 0.91 and 1.9 g.kg−¹ for LNC, and 0.86 and 0.17 m for PH. It was also demonstrated that VIs contributed more to the algorithm’s performances than individual spectral bands. This study concludes that the RF model is appropriate to predict both agronomic variables in maize and may help farmers to monitor their plants based upon their LNC and PH diagnosis and use this knowledge to improve their production rates in the subsequent seasons.
The current challenge of corn (Zea mays L.) crops is to reach high yield to supply the world's demand for food, especially under different fertilization regimes and using the latest technology. We hypothesized that wavelengths and vegetation indices have a linear relationship with agronomic variables in corn. Our objectives were to verify the formation of super-traits and to study the association between wavelengths and vegetation indices with agronomic traits in corn cultivated under high and low topdressing N. The experiments were carried out in two crop seasons using a randomized block design with three replicates in a factorial scheme (11 genotypes × 2 contrasting levels of N: low, 60 kg ha -1 and high, 180 kg ha -1 ). At full bloom, the spectral variables green (550 nm), red (660 nm), red-edge (735 nm), and near-infrared (790 nm) and the vegetation indices normalized difference vegetation index (NDVI), normalized difference red-edge index (NDRE), green normalized difference vegetation index (GNDVI), and soil-adjusted vegetation index (SAVI) were evaluated. Agronomic traits evaluated were leaf N, plant height, first pod height, stem diameter, cob length, rows per cob, grains per row, and grain yield. Results showed that SAVI, GNDVI, NDVI, and NDRE and red-edge and red were associated with agronomic traits in corn. The association between the agronomic traits evaluated here can be used to estimate the leaf N content and corn yield. INTRODUCTIONThe world demand for corn (Zea mays L.) consumption has increased, which has led to the need for increased production.To meet this growing demand, it is necessary to invest in crop
Using remote sensing combined with machine learning (ML) techniques is a promising approach to classify soybean cultivars. Therefore, the objectives of this study are (i) to verify which input dataset configuration (using only spectral bands, only vegetation indices, or both) is more accurate in the identification of soybean cultivars, and (ii) to verify which ML technique is more accurate in the identification of soybean cultivars. Information was extracted from five central irrigation pivots in the same region and with the same sowing date in the 2015/2016 crop year, in which each pivot was cultivated with a different cultivar, in which the cultivars used were: CV1—P98y12 RR, CV2—Desafio RR, CV3—M6410 IPRO, CV4—M7110 IPRO, and CV5—NA5909 RR. A cloud-free orbital image of the site was acquired from the Google Earth Engine platform. In addition to the spectral bands alone, a total of 13 vegetation indices were calculated. The models tested were: artificial neural networks (ANN), radial basis function network (RBF), decision tree algorithms J48 (DT) and reduced error pruning tree (REP), random forest (RF), and support vector machine (SVM). The five soybean cultivars were classified by the six-machine learning (ML) models in stratified randomized cross-validation with k-fold = 10 and 10 repetitions (100 runs for each model). After obtaining the r and MAE statistics, analysis of variance was performed considering a 6 × 3 factorial scheme (models versus inputs) with 10 repetitions (folds). The means were grouped by the Scott–Knott test at 5% probability. The spectral bands were the most accurate among the tested inputs in the identification of soybean cultivars. ANN was the most accurate model in identifying soybean cultivars.
Hydroponic forage is an alternative to feed the animal in times of drought quickly. Thus, the objective of this work was to evaluate the development of hydroponic forage of corn and millet irrigated with mineral and organic solutions during the winter season in the Cerrado-Pantanal ecotone, seeking to determine the species and the most suitable solution for the region at that time. The experimental design was in randomized blocks, in a split plot scheme. The plots were the solutions (mineral and organic) and the subplots were the populations of corn, millet and black mucuna and their respective proportions, totaling 12 treatments, with four replications. At harvest, the production of green and dry matter production was carried out and a bromatological analysis of the aerial part and substrate was carried out, determining crude protein, neutral detergent fiber, acid detergent fiber and mineral matter. The chemical evaluation of the organic solution was carried out in a fertigation analysis laboratory. Corn forage under mineral solution irrigation obtained better crude protein contents. The substrate that obtained the highest crude protein and the lowest fiber content was in the subplot with 100% millet for both solutions.
The Brazilian government intends to complete the paving of the BR-319 highway, which connects Porto Velho in the deforestation arc region with Manaus in the middle of the Amazon Forest. This paving is being planned despite environmental legislation, and there is concern that its effectiveness will cause additional deforestation, threatening large portions of forest, conservation units (CUs), and indigenous lands (ILs) in the surrounding areas. In this study, we evaluated environmental degradation along the BR-319 highway from 2008 to 2020 and verified whether highway maintenance has contributed to deforestation. For this purpose, we created a 20 km buffer adjacent to the BR-319 highway and evaluated variables extracted from remote sensing information between 2008 and 2020. Fire foci, burned areas, and rainfall data were used to calculate a drought index using statistical tests for a time series. Furthermore, these were related to data on deforestation, CUs, and ILs using principal component analysis and Pearson’s correlation. Our results showed that 743 km2 of forest was deforested during the period evaluated, most of which occurred in the last four years. A total of 16,472 fire foci were identified. Both deforestation and fire foci occurred mainly outside the CUs and ILs. The most affected areas were close to capital cities, and after resuming road maintenance in 2015, deforestation increased outside the capital cities. Current government policy for Amazon occupation promotes deforestation and will compromise Brazil’s climate goals of reducing greenhouse gas (GHG) emissions and deforestation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.