The use of unmanned aerial systems (UAS) as remote-sensing platforms has tremendous potential for obtaining detailed, site-specific descriptions of crop features, which would be very useful for precision agriculture. In sugarcane plantations, for example, cane height can be an indicator of yield and other parameters because it is highly influenced by the soil, total sugar content, leaf nitrogen content, temperature and light intensity. This article describes the generation of crop surface models (CSMs) from high-resolution images that were obtained using a UAS to estimate sugarcane height. Using a UAS with an on-board RGB camera, we created densified three-dimensional point clouds of the study area in two different flight line directions (North/South and East/West) using structure from motion (SfM) with multi-view stereo (MVS). Then, the digital surface model (DSM) and digital terrain model (DTM) were extracted and used to create CSMs. Maps of sugarcane height were created based on this information. We investigated the influences of different flight line directions (N/S and E/W) on sugarcane height estimations and their accuracy by comparing our maps with ground references. From the validation conducted using both flight lines, the average heights were closer to the field-verified data. The resulting maps showed differences in sugarcane height that were confirmed by field measurements. This method has potential for future use by sugarcane-related industries, researchers and farmers to estimate average crop height.

Fast and accurate quantification of the available pasture biomass is essential to support grazing management decisions in intensively managed fields. The increasing temporal and spatial resolutions offered by the new generation of orbital platforms, such as Planet CubeSat satellites, have improved the capability of monitoring pasture biomass using remotely sensed data. Here, we assessed the feasibility of using spectral and textural information derived from PlanetScope imagery for estimating pasture aboveground biomass (AGB) and canopy height (CH) in intensively managed fields and the potential for enhanced accuracy by applying the extreme gradient boosting (XGBoost) algorithm. Our results demonstrated that the texture measures enhanced AGB and CH estimations compared to the performance obtained using only spectral bands or vegetation indices. The best results were found by employing the XGBoost models based only on texture measures. These models achieved moderately high accuracy to predict pasture AGB and CH, explaining 65% and 89% of AGB (root mean square error (RMSE) = 26.52%) and CH (RMSE = 20.94%) variability, respectively. This study demonstrated the potential of using texture measures to improve the prediction accuracy of AGB and CH models based on high spatiotemporal resolution PlanetScope data in intensively managed mixed pastures.

Timely and efficient land-cover mapping is of high interest, especially in agricultural landscapes. Classification based on satellite images over the season, while important for cropland monitoring, remains challenging in subtropical agricultural areas due to the high diversity of management systems and seasonal cloud cover variations. This work presents supervised object-based classifications over the year at 2-month time-steps in a heterogeneous region of 12,000 km² in the Sao Paulo region of Brazil. Different methods and remote-sensing datasets were tested with the random forest algorithm, including optical and radar data, time series of images, and cloud gap-filling methods. The final selected method demonstrated an overall accuracy of approximately 0.84, which was stable throughout the year, at the more detailed level of classification; confusion mainly occurred among annual crop classes and soil classes. We showed in this study that the use of time series was useful in this context, mainly by including a small number of highly discriminant images. Such important images were eventually distant in time from the prediction date, and they corresponded to a high-quality image with low cloud cover. Consequently, the final classification accuracy was not sensitive to the cloud gap-filling method, and simple median gap-filling or linear interpolations with time were sufficient. Sentinel-1 images did not improve the classification results in this context. For within-season dynamic classes, such as annual crops, which were more difficult to classify, field measurement efforts should be densified and planned during the most discriminant window, which may not occur during the crop vegetation peak.

Pixelwise image classification based on time series profiles has been very effective in several applications. In this letter, we investigate recently proposed image-based time series encoding approaches [e.g., Gramian angular summation field/Gramian angular difference field (GASF/GADF) and Markov transition field (MTF)] to support the identification of eucalyptus regions in remote sensing images. We perform a comparative study concerning the combination of image-based representations suitable for encoding the most important time series patterns with the ability of state-of-the-art deep-learning-based approaches for characterizing image visual properties. The comparative study demonstrates that the evaluated image representations, combined with different deep learning feature extractors lead to highly effective classification results, which are superior to those of recently proposed methods for time-series-based eucalyptus plantation detection.

It is expected that Brazil could play an important role in biojet fuel (BJF) production in the future due to the long experience in biofuel production and the good agro‐ecological conditions. However, it is difficult to quantify the techno‐economic potential of BJF because of the high spatio‐temporal variability of available land, biomass yield, and infrastructure as well as the technological developments in BJF production pathways. The objective of this research is to assess the recent and future techno‐economic potential of BJF production in Brazil and to identify location specific optimal combinations of biomass crops and technological conversion pathways. In total, thirteen production routes (supply chains) are assessed through the combination of various biomass crops and BJF technologies. We consider temporal land use data to identify potential land availability for biomass production. With the spatial distribution of the land availability and potential yield of biomass crops, biomass production potential and costs are calculated. The BJF production cost are calculated by taking into account the development in the technological pathways and in plant scales. We estimate the techno‐economic potential by determining the minimum BJF total costs and comparing this with the range of fossil jet fuel prices. The techno‐economic potential of BJF production ranges from 0 to 6.4 EJ in 2015 and between 1.2 – 7.8 EJ in 2030, depending on the reference fossil jet fuel price, which varies from 19 US$/GJ to 65 US$/GJ across the airports. The techno‐economic potential consists of a diverse set of production routes. The Northeast and Southeast region of Brazil present the highest potentials with several viable production routes, whereas the remaining regions only have a few promising production routes. The maximum techno‐economic potential of BJF in Brazil could meet almost half of the projected global jet fuel demand towards 2030.

This article addresses the pixelwise classification problem based on temporal profiles, which are encoded in 2-D representations based on recurrence plots, Gramian angular/ difference fields, and Markov transition field. We propose a multirepresentational fusion scheme that exploits the complementary view provided by those time series representations and different data-driven feature extractors and classifiers. We validate our ensemble scheme in the problem related to the classification of eucalyptus plantations in remote sensing images. Achieved results demonstrate that our proposal overcomes recently proposed baselines, and now represents the new state-of-the-art classification solution for the target dataset.