Incorporation of Unmanned Aerial Vehicle (UAV) Point Cloud Products into Remote Sensing Evapotranspiration Models

Machine learning assisted remote forestry health assessment: a comprehensive state of the art review

Forests are suffering water stress due to climate change; in some parts of the globe, forests are being exposed to the highest temperatures historically recorded. Machine learning techniques combined with robotic platforms and artificial vision systems have been used to provide remote monitoring of the health of the forest, including moisture content, chlorophyll, and nitrogen estimation, forest canopy, and forest degradation, among others. However, artificial intelligence techniques evolve fast associated with the computational resources; data acquisition, and processing change accordingly. This article is aimed at gathering the latest developments in remote monitoring of the health of the forests, with special emphasis on the most important vegetation parameters (structural and morphological), using machine learning techniques. The analysis presented here gathered 108 articles from the last 5 years, and we conclude by showing the newest developments in AI tools that might be used in the near future.

An intelligent monitoring system of diseases and pests on rice canopy

Accurate and timely surveys of rice diseases and pests are important to control them and prevent the reduction of rice yields. The current manual survey method of rice diseases and pests is time-consuming, laborious, highly subjective and difficult to trace historical data. To address these issues, we developed an intelligent monitoring system for detecting and identifying the disease and pest lesions on the rice canopy. The system mainly includes a network camera, an intelligent detection model of diseases and pests on rice canopy, a web client and a server. Each camera of the system can collect rice images in about 310 m² of paddy fields. An improved model YOLO-Diseases and Pests Detection (YOLO-DPD) was proposed to detect three lesions of Cnaphalocrocis medinalis, Chilo suppressalis, and Ustilaginoidea virens on rice canopy. The residual feature augmentation method was used to narrow the semantic gap between different scale features of rice disease and pest images. The convolution block attention module was added into the backbone network to enhance the regional disease and pest features for suppressing the background noises. Our experiments demonstrated that the improved model YOLO-DPD could detect three species of disease and pest lesions on rice canopy at different image scales with an average precision of 92.24, 87.35 and 90.74%, respectively, and a mean average precision of 90.11%. Compared to RetinaNet, Faster R-CNN and Yolov4 models, the mean average precision of YOLO-DPD increased by 18.20, 6.98, 6.10%, respectively. The average detection time of each image is 47 ms. Our system has the advantages of unattended operation, high detection precision, objective results, and data traceability.

Evapotranspiration Acquired with Remote Sensing Thermal-Based Algorithms: A State-of-the-Art Review

Almost fifty years have passed since the idea to retrieve a value for Evapotranspiration (ET) using remote sensing techniques was first considered. Numerous ET models have been proposed, validated and improved along these five decades, as the satellites and sensors onboard were enhanced. This study reviews most of the efforts in the progress towards providing a trustworthy value of ET by means of thermal remote sensing data. It starts with an in-depth reflection of the surface energy balance concept and of each of its terms, followed by the description of the approaches taken by remote sensing models to estimate ET from it in the last thirty years. This work also includes a chronological review of the modifications suggested by several researchers, as well as representative validations studies of such ET models. Present limitations of ET estimated with remote sensors onboard orbiting satellites, as well as at surface level, are raised. Current trends to face such limitations and a future perspective of the discipline are also exposed, for the reader’s inspiration.

Potentials of Low-Budget Microdrones: Processing 3D Point Clouds and Images for Representing Post-Industrial Landmarks in Immersive Virtual Environments

Post-industrial areas in Europe, such as the Rhine-Ruhr Metropolitan region in Germany, include cultural heritage sites fostering local and regional identities with the industrial past. Today, these landmarks are popular places of interest for visitors. In addition to portable camera devices, low-budget ultra-lightweight unmanned aerial vehicles, such as micro quadcopter drones, are on their way to being established as mass photography equipment. This low-cost hardware is not only useful for recreational usage but also supports individualized remote sensing with optical images and facilitates the acquisition of 3D point clouds of the targeted object(s). Both data sets are valuable and accurate geospatial data resources for further processing of textured 3D models. To experience these 3D models in a timely way, these 3D visualizations can directly be imported into game engines. They can be extended with modern interaction techniques and additional (semantic) information. The visualization of the data can be explored in immersive virtual environments, which allows, for instance, urban planners to use low-cost microdrones to 3D map the human impact on the environment and preserve this status in a 3D model that can be analyzed and explored in following steps. A case example of the old wage hall of the Zeche "Bonifacius" (Essen, Germany) with its simple building structure showed that it is possible to generate a detailed and accurate 3D model based on the microdrone data. The point cloud which the 3D model of the old wage hall was based on represented partly better data accuracy than the point clouds derived from airborne laser scanning and offered by public agencies as open data. On average, the distance between the point clouds was 0.7 m, while the average distance between the airborne laser scanning point cloud and the 3D model was -0.02 m. Matching high-quality textures of the building facades brings in a new aspect of 3D data quality which can be adopted when creating immersive virtual environments using the Unity engine. The example of the wage hall makes it clear that the use of low-cost drones and the subsequent data processing can result in valuable sources of point clouds and textured 3D models.

Evapotranspiration partitioning assessment using a machine-learning-based leaf area index and the two-source energy balance model with sUAV information

Accurate quantification of the partitioning of evapotranspiration (ET) into transpiration and evaporation fluxes is necessary to understanding ecosystem interactions among carbon, water, and energy flux components. ET partitioning can also support the description of atmosphere and land interactions and provide unique insights into vegetation water status. Previous studies have identified leaf area index (LAI) estimation as a key descriptor of biomass conditions needed for the estimation of transpiration and evaporation. LAI estimation in clumped vegetation systems, such as vineyards and orchards, has proven challenging and is strongly related to crop phenological status and canopy management. In this study, a feature extraction model based on previous research was built to generate a total of 202 preliminary variables at a 3.6-by-3.6-meter-grid scale based on submeter-resolution information from a small Unmanned Aerial Vehicle (sUAV) in four commercial vineyards across California. Using these variables, a machine learning model called eXtreme Gradient Boosting (XGBoost) was successfully built for LAI estimation. The XGBoost built-in function requires only six variables relating to vegetation indices and temperature to produce high-accuracy LAI estimation for the vineyard. Using the six-variable XGBoost-based LAI map, two versions of the Two-Source Energy Balance (TSEB) model, TSEB-PT and TSEB-2T were used for energy balance and ET partitioning. Comparing these results with the Eddy-Covariance (EC) tower data, showed that TSEB-PT outperforms TSEB-2T on the estimation of sensible heat flux (within 13% relative error) and surface heat flux (within 34% relative error), while TSEB-2T outperforms TSEB-PT on the estimation of net radiation (within 14% relative error) and latent heat flux (within 2% relative error). For the mature vineyard (north block), TSEB-2T performs better than TSEB-PT in partitioning the canopy latent heat flux with 6.8% relative error and soil latent heat flux with 21.7% relative error; however, for the younger vineyard (south block), TSEB-PT performs better than TSEB-2T in partitioning the canopy latent heat flux with 11.7% relative error and soil latent heat flux with 39.3% relative error.

Construction of an evapotranspiration model and analysis of spatiotemporal variation in Xilin River Basin, China

Surface evapotranspiration is a water exchange process between the atmosphere, biosphere, and hydrosphere. Accurate evapotranspiration estimations in arid and semi-arid regions are important for monitoring droughts and protecting the ecological environment. The main objective of this study is to build an evapotranspiration estimation model suitable for an effective scientific and objective evaluation of water consumption in the arid and semi-arid regions of the Xilin River Basin based on comprehensive parameters, including meteorological parameters, vegetation coverage, and soil water content. In this study, the community evapotranspiration model was initially constructed using field data, which was then expanded for applicability to the Xilin River Basin based on Geographic Information System technology and spatial heterogeneity characteristics of remote sensing data; both models were significant at the 0.05 level. The monthly evapotranspiration values in July during 2000-2017 and those from April to September (growing season) during the dry, normal, and wet years were calculated using the model at the basin scale. The evapotranspiration showed a generally increasing trend, which was consistent with the fluctuation trend in precipitation in July during 2000-2017. The trend curve for evapotranspiration was gentle during the growing season in dry years, but steep during wet years. The evapotranspiration was the lowest in April, with negligible spatial variations throughout the Xilin River Basin. During May-July, the evapotranspiration was higher than that in other months, in the following order: upper reaches > middle reaches > lower reaches; this was consistent with the vegetation coverage. The evapotranspiration declined and spatial variations were not evident during August-September. The results of this study provide a reference for evapotranspiration model construction and a scientific basis for evaluating regional water resources and protecting the ecological environment.

The Unmanned Systems Research Laboratory (USRL): A New Facility for UAV-Based Atmospheric Observations

The Unmanned Systems Research Laboratory (USRL) of the Cyprus Institute is a new mobile exploratory platform of the EU Research Infrastructure Aerosol, Clouds and Trace Gases Research InfraStructure (ACTRIS). USRL offers exclusive Unmanned Aerial Vehicle (UAV)-sensor solutions that can be deployed anywhere in Europe and beyond, e.g., during intensive field campaigns through a transnational access scheme in compliance with the drone regulation set by the European Union Aviation Safety Agency (EASA) for the research, innovation, and training. UAV sensor systems play a growing role in the portfolio of Earth observation systems. They can provide cost-effective, spatial in-situ atmospheric observations which are complementary to stationary observation networks. They also have strong potential for calibrating and validating remote-sensing sensors and retrieval algorithms, mapping close-to-the-ground emission point sources and dispersion plumes, and evaluating the performance of atmospheric models. They can provide unique information relevant to the short- and long-range transport of gas and aerosol pollutants, radiative forcing, cloud properties, emission factors and a variety of atmospheric parameters. Since its establishment in 2015, USRL is participating in major international research projects dedicated to (1) the better understanding of aerosol-cloud interactions, (2) the profiling of aerosol optical properties in different atmospheric environments, (3) the vertical distribution of air pollutants in and above the planetary boundary layer, (4) the validation of Aeolus satellite dust products by utilizing novel UAV-balloon-sensor systems, and (5) the chemical characterization of ship and stack emissions. A comprehensive overview of the new UAV-sensor systems developed by USRL and their field deployments is presented here. This paper aims to illustrate the strong scientific potential of UAV-borne measurements in the atmospheric sciences and the need for their integration in Earth observation networks.

Actual Evapotranspiration from UAV Images: A Multi-Sensor Data Fusion Approach

Multispectral imaging using Unmanned Aerial Vehicles (UAVs) has changed the pace of precision agriculture. Actual evapotranspiration (ETa) from the very high spatial resolution of UAV images over agricultural fields can help farmers increase their production at the lowest possible cost. ETa estimation using UAVs requires a full package of sensors capturing the visible/infrared and thermal portions of the spectrum. Therefore, this study focused on a multi-sensor data fusion approach for ETa estimation (MSDF-ET) independent of thermal sensors. The method was based on sharpening the Landsat 8 pixels to UAV spatial resolution by considering the relationship between reference ETa fraction (ETrf) and a Vegetation Index (VI). Four Landsat 8 images were processed to calculate ETa of three UAV images over three almond fields. Two flights coincided with the overpasses and one was in between two consecutive Landsat 8 images. ETrf was chosen instead of ETa to interpolate the Landsat 8-derived ETrf images to obtain an ETrf image on the UAV flight. ETrf was defined as the ratio of ETa to grass reference evapotranspiration (ETr), and the VIs tested in this study included the Normalized Difference Vegetation Index (NDVI), Soil Adjusted Vegetation Index (SAVI), Enhanced Vegetation Index (EVI), Normalized Difference Water Index (NDWI), and Land Surface Water Index (LSWI). NDVI performed better under the study conditions. The MSDF-ET-derived ETa showed strong correlations against measured ETa, UAV- and Landsat 8-based METRIC ETa. Also, visual comparison of the MSDF-ET ETa maps was indicative of a promising performance of the method. In sum, the resulting ETa had a higher spatial resolution compared with thermal-based ETa without the need for the Albedo and hot/cold pixels selection procedure. However, wet soils were poorly detected, and in cases of continuous cloudy Landsat pixels the long interval between the images may cause biases in ETa estimation from the MSDF-ET method. Generally, the MSDF-ET method reduces the need for very high resolution thermal information from the ground, and the calculations can be conducted on a moderate-performance computer system because the main image processing is applied on Landsat images with coarser spatial resolutions.

Automatic Grapevine Trunk Detection on UAV-Based Point Cloud

The optimisation of vineyards management requires efficient and automated methods able to identify individual plants. In the last few years, Unmanned Aerial Vehicles (UAVs) have become one of the main sources of remote sensing information for Precision Viticulture (PV) applications. In fact, high resolution UAV-based imagery offers a unique capability for modelling plant’s structure making possible the recognition of significant geometrical features in photogrammetric point clouds. Despite the proliferation of innovative technologies in viticulture, the identification of individual grapevines relies on image-based segmentation techniques. In that way, grapevine and non-grapevine features are separated and individual plants are estimated usually considering a fixed distance between them. In this study, an automatic method for grapevine trunk detection, using 3D point cloud data, is presented. The proposed method focuses on the recognition of key geometrical parameters to ensure the existence of every plant in the 3D model. The method was tested in different commercial vineyards and to push it to its limit a vineyard characterised by several missing plants along the vine rows, irregular distances between plants and occluded trunks by dense vegetation in some areas, was also used. The proposed method represents a disruption in relation to the state of the art, and is able to identify individual trunks, posts and missing plants based on the interpretation and analysis of a 3D point cloud. Moreover, a validation process was carried out allowing concluding that the method has a high performance, especially when it is applied to 3D point clouds generated in phases in which the leaves are not yet very dense (January to May). However, if correct flight parametrizations are set, the method remains effective throughout the entire vegetative cycle.