The development of lightweight sensors compatible with mini unmanned aerial vehicles (UAVs) has expanded the agronomical applications of remote sensing. Of particular interest in this paper are thermal sensors based on lightweight microbolometer technology. These are mainly used to assess crop water stress with thermal images where an accuracy greater than 1 °C is necessary. However, these sensors lack precise temperature control, resulting in thermal drift during image acquisition that requires correction. Currently, there are several strategies to manage thermal drift effect. However, these strategies reduce useful flight time over crops due to the additional in-flight calibration operations. This study presents a drift correction methodology for microbolometer sensors based on redundant information from multiple overlapping images. An empirical study was performed in an orchard of high-density hedgerow olive trees with flights at different times of the day. Six mathematical drift correction models were developed and assessed to explain and correct drift effect on thermal images. Using the proposed methodology, the resulting thermally corrected orthomosaics yielded a rate of error lower than 1° C compared to those where no drift correction was applied.
Wildfires are becoming more frequent in different parts of the globe, and the ability to predict when and where they will occur is a complex process. Identifying wildfire events with high probability of becoming a large wildfire is an important task for supporting initial attack planning. Different methods, including those that are physics-based, statistical, and based on machine learning (ML) are used in wildfire analysis. Among the whole, those based on machine learning are relatively novel. In addition, because the number of wildfires is much greater than the number of large wildfires, the dataset to be used in a ML model is imbalanced, resulting in overfitting or underfitting the results. In this manuscript, we propose to generate synthetic data from variables of interest together with ML models for the prediction of large wildfires. Specifically, five synthetic data generation methods have been evaluated, and their results are analyzed with four ML methods. The results yield an improvement in the prediction power when synthetic data are used, offering a new method to be taken into account in Decision Support Systems (DSS) when managing wildfires.
Poppy (also common poppy or corn poppy; Papaver rhoeas L., PAPRH) is one of the most harmful weeds in winter cereals. Knowing the precise and accurate location of weeds is essential for developing effective site-specific weed management (SSWM) for optimized herbicide use. Among the available tools for weed mapping, deep learning (DL) is used for its accuracy and ability to work in complex scenarios. Crops represent intricate situations for weed detection, as crop residues, occlusion of weeds, or spectral similarities between crop and weed seedlings are frequent. Timely discrimination of weeds is needed, because postemergence herbicides are used just when weeds and crops are at an early growth stage. This study addressed P. rhoeas early detection in wheat (Triticum spp.) by comparing the performance of six DL-based object-detection models focused on the “You Only Look Once” (YOLO) architecture (v3 to v5) using proximal RGB images to train the models. The models were assessed using open-source software, and evaluation offered a range of results for quality of recognition of P. rhoeas as well as computational capacity during the inference process. Of all the models, YOLOv5s performed best in the testing phase (75.3%, 76.2%, and 77% for F1-score, mean average precision, and accuracy, respectively). These results indicated that under real field conditions, DL-based object-detection strategies can identify P. rhoeas at an early stage, providing accurate information for developing SSWM.
The development of unmanned aerial vehicle (UAV) technology and the miniaturization of sensors have changed the way remote sensing (RS) is used, popularizing this geoscientific discipline in other fields, such as precision agriculture. This makes it necessary to implement the use of these technologies in teaching RS alongside the classical platforms (satellite and manned aircraft). This manuscript describes how The Higher Technical School of Agricultural Engineering at the University of Córdoba (Spain) has introduced UAV RS into the academic program by way of project-based learning (PBL). It also presents the basic characteristics of PBL, the design of the subject, the description of the teacher-guided and self-directed activities, as well as the degree of student satisfaction. The teaching and learning objectives of the subject are to learn how to determine the vigor, temperature, and water stress of a crop through the use of RGB, multispectral, and thermographic sensors onboard a UAV platform. From the onset, students are motivated, actively participate in the tasks related to the realization of UAV flights, and subsequent processing and analysis of the registered images. Students report that PBL is more engaging and allows them to develop a better understanding of RS.
The disease caused by SARS-CoV-2 has affected many countries and regions. In order to contain the spread of infection, many countries have adopted lockdown measures. As a result, SARS-CoV-2 has negatively influenced economies on a global scale and has caused a significant impact on the environment. In this study, changes in the concentration of the pollutant Nitrogen Dioxide (NO2) within the lockdown period were examined as well as how these changes relate to the Spanish population. NO2 is one of the reactive nitrogen oxides gases resulting from both anthropogenic and natural processes. One major source in urban areas is the combustion of fossil fuels from vehicles and industrial plants, both of which significantly contribute to air pollution. The long-term exposure to NO2 can also cause severe health problems. Remote sensing is a useful tool to analyze spatial variability of air quality. For this purpose, Sentinel-5P images registered from January to April of 2019 and 2020 were used to analyze spatial distribution of NO2 and its evolution under the lockdown measures in Spain. The results indicate a significant correlation between the population’s activity level and the reduction of NO2 values.
Plant phenology is affected by climate conditions and therefore provides a sensitive indicator to changes in climate. Studying the evolution and change in plant phenology aids in a better understanding of and predicting changes in ecosystems. Vegetation Indices (VIs) have been recognized for their utility in indicating vegetation activity. Understanding climatic variables and their relationship to VI support the knowledge base of how ecosystems are changing under a new climatic scenario. This study evaluates grassland growth phenology in the Biobio, Chile, biweekly with Moderate Resolution Imaging Spectroradiometer (MODIS) Normalized Difference Vegetation Index (NDVI) time series. Four growth parameters for the six agro-climatic regions were analyzed from 2001 to 2020: start and end of the season, time and value of maximum NDVI. For this purpose, the NDVI time series were smoothed using Savitzky–Golay filtering. In addition, by using monthly gridded database climate data, we studied correlations between phenology markers and rainfall, maximum temperature and minimum temperature. The results show that both the start and end of the growing season did not significantly change; however, all agro-climatic regions grow faster and more vigorously. Thus, climatic conditions in Biobio have become more conducive to grassland growth over the 2001–2020 period.