Search

We provide the first method allowing to retrieve spaceborne SIF maps at 30 m ground resolution with a strong correlation ($r^2=0.6$) to high-quality airborne estimates of sun-induced fluorescence (SIF). SIF estimates can provide explanatory information for many tasks related to agricultural management and physiological studies. While SIF products from airborne platforms are accurate and spatially well resolved, the data acquisition of such products remains science-oriented and limited to temporally constrained campaigns. Spaceborne SIF products on the other hand are available globally with often sufficient revisit times. However, the spatial resolution of spaceborne SIF products is too small for agricultural applications. In view of ESA's upcoming FLEX mission we develop a method for SIF retrieval in the O$_2$-A band of hyperspectral DESIS imagery to provide first insights for spaceborne SIF retrieval at high spatial resolution. To this end, we train a simulation-based self-supervised network with a novel perturbation based regularizer and test performance improvements under additional supervised regularization of atmospheric variable prediction. In a validation study with corresponding HyPlant derived SIF estimates at 740 nm we find that our model reaches a mean absolute difference of 0.78 mW / nm / sr / m$^2$., Comment: submitted to ECCV CVPPA 2024, 14 pages, 8 figures

This article presents GrowliFlower, a georeferenced, image-based UAV time series dataset of two monitored cauliflower fields of size 0.39 and 0.60 ha acquired in 2020 and 2021. The dataset contains RGB and multispectral orthophotos from which about 14,000 individual plant coordinates are derived and provided. The coordinates enable the dataset users the extraction of complete and incomplete time series of image patches showing individual plants. The dataset contains collected phenotypic traits of 740 plants, including the developmental stage as well as plant and cauliflower size. As the harvestable product is completely covered by leaves, plant IDs and coordinates are provided to extract image pairs of plants pre and post defoliation, to facilitate estimations of cauliflower head size. Moreover, the dataset contains pixel-accurate leaf and plant instance segmentations, as well as stem annotations to address tasks like classification, detection, segmentation, instance segmentation, and similar computer vision tasks. The dataset aims to foster the development and evaluation of machine learning approaches. It specifically focuses on the analysis of growth and development of cauliflower and the derivation of phenotypic traits to foster the development of automation in agriculture. Two baseline results of instance segmentation at plant and leaf level based on the labeled instance segmentation data are presented. The entire data set is publicly available., Comment: 23 pages, 21 figures, 5 tables

Understanding the adaptation process of plants to drought stress is essential in improving management practices, breeding strategies as well as engineering viable crops for a sustainable agriculture in the coming decades. Hyper-spectral imaging provides a particularly promising approach to gain such understanding since it allows to discover non-destructively spectral characteristics of plants governed primarily by scattering and absorption characteristics of the leaf internal structure and biochemical constituents. Several drought stress indices have been derived using hyper-spectral imaging. However, they are typically based on few hyper-spectral images only, rely on interpretations of experts, and consider few wavelengths only. In this study, we present the first data-driven approach to discovering spectral drought stress indices, treating it as an unsupervised labeling problem at massive scale. To make use of short range dependencies of spectral wavelengths, we develop an online variational Bayes algorithm for latent Dirichlet allocation with convolved Dirichlet regularizer. This approach scales to massive datasets and, hence, provides a more objective complement to plant physiological practices. The spectral topics found conform to plant physiological knowledge and can be computed in a fraction of the time compared to existing LDA approaches., Comment: Appears in Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence (UAI2012)

UNKNOWN

The first European Space Agency (ESA) and NASA collaboration in an airborne campaign to support ESA's FLuorescence EXplorer (FLEX) mission was conducted in North Carolina, USA during September-October 2013 (FLEX-US 2013) at the Parker Tract Loblolly Pine (LP) Plantation (Plymouth, NC, USA). This campaign combined two unique airborne instrument packages to obtain simultaneous observations of solar-induced fluorescence (SIF), LiDAR-based canopy structural information, visible through shortwave infrared (VSWIR) reflectance spectra, and surface temperature, to advance vegetation studies of carbon cycle dynamics and ecosystem health. We obtained statistically significant results for fluorescence, canopy temperature, and tower fluxes from data collected at four times of day over two consecutive autumn days across an age class chronosequence. Both the red fluorescence (F685) and far-red fluorescence (F740) radiances had highest values at mid-day, but their fluorescence yields exhibited different diurnal responses across LP age classes. The diurnal trends for F685 varied with forest canopy temperature difference (canopy minus air), having a stronger daily amplitude change for young vs. old canopies. The Photochemical Reflectance Index (PRI) was positively correlated with this temperature variable over the diurnal cycle. Tower measurements from mature loblolly stand showed the red/far-red fluorescence ratio was linearly related to canopy light use efficiency (LUE) over the diurnal cycle, but performed even better for the combined morning/afternoon (without midday) observations. This study demonstrates the importance of diurnal observations for interpretation of fluorescence dynamics, the need for red fluorescence to understand canopy physiological processes, and the benefits of combining fluorescence, reflectance, and structure information to clarify canopy function versus structure characteristics for a coniferous forest.

The Fluorescence Explorer (FLEX) mission has been recently selected as the 8th Earth Explorer by the European Space Agency (ESA). It will be the first mission specifically designed to measure from space vegetation fluorescence emission, by making use of very high spectral resolution imaging spectroscopy techniques. Vegetation fluorescence is the best proxy to actual vegetation photosynthesis which can be measurable from space, allowing an improved quantification of vegetation carbon assimilation and vegetation stress conditions, thus having key relevance for global mapping of ecosystems dynamics and aspects related with agricultural production and food security. The FLEX mission carries the FLORIS spectrometer, with a spectral resolution in the range of 0.3 nm, and is designed to fly in tandem with Copernicus Sentinel-3, in order to provide all the necessary spectral / angular information to disentangle emitted fluorescence from reflected radiance, and to allow proper interpretation of the observed fluorescence spatial and temporal dynamics.

Remote Sensing of Sun-Induced Chlorophyll Fluorescence (SIF) is a research field of growing interest because it offers the potential to quantify actual photosynthesis and to monitor plant status. New satellite missions from the European Space Agency, such as the Earth Explorer 8 FLuorescence EXplorer (FLEX) mission-scheduled to launch in 2022 and aiming at SIF mapping-and from the National Aeronautics and Space Administration (NASA) such as the Orbiting Carbon Observatory-2 (OCO-2) sampling mission launched in July 2014, provide the capability to estimate SIF from space. The detection of the SIF signal from airborne and satellite platform is difficult and reliable ground level data are needed for calibration/validation. Several commercially available spectroradiometers are currently used to retrieve SIF in the field. This study presents a comparison exercise for evaluating the capability of four spectroradiometers to retrieve SIF. The results show that an accurate far-red SIF estimation can be achieved using spectroradiometers with an ultrafine resolution (less than 1 nm), while the red SIF estimation requires even higher spectral resolution (less than 0.5 nm). Moreover, it is shown that the Signal to Noise Ratio (SNR) plays a significant role in the precision of the far-red SIF measurements.

Unmanned Aerial Vehicles (UAVs) open new opportunities because data acquisition is timely flexible and the system can be operated very easily. The technology can provide plant breeders, insurance companies or farmers timely detailed information on plant traits with low monetary costs. In this study the potential of ultra-high spatially resolved UAV image data was investigated to assess the canopy height (CH) of barley using Structure from Motion (SfM) techniques. The results showed, that UAV derived information on the spatial height distribution of the canopy was influenced by the canopy structure and sowing density. In contrast classical plant height measurements only representing single points in the field. In conclusion, the UAV based CH is an autonomous trait which can only be compared with measured plant heights in field to a limited extent. The UAV derived CH was further used to determine the lodging percentage and the lodging severity of barley. Unmanned Aerial Vehicles (UAVs) open new opportunities because data acquisition is timely flexible and the system can be operated very easily. The technology can provide plant breeders, insurance companies or farmers timely detailed information on plant traits with low monetary costs. Especially breeding trials are extensive to monitor resulting in an increasing need for a faster selection of superior lines. In the following presentation the potential of ultra-high spatially resolved UAV image data was investigated to assess the canopy height (CH) of barley using Structure from Motion (SfM) techniques. The UAV derived CH was used to determine the lodging percentage and the lodging severity. Lodging is defined as the permanent displacement of a plant from the upright position. It is a major problem of cereals in agriculture because it leads to qualitative and quantitative yield losses up to 45 %. Traditionally lodg ing assessment is based on field observations that are neither cost-efficient nor objective. For that reason, an objective threshold approach was proposed in this study to overcome subjective estimates and improve the accuracy in lodging determination. Compared to manual reference measurement the UAV based lodging percentage provided a very high correlation (R² = 0.96) when applied to breeding trials. As a proof of concept the method was additionally applied to a classical farmer field and let only to a slight overestimation of 2 % compared to reference data. Building on the parameter lodging percentage an approach was developed that allowed the assessment of lodging severity (R² = 0.92), an information that is important to estimate the yield impairment. The assessment of the two lodging parameters was tested on date sets with different ground sampling distances (GSDs). The strongest accuracies could be achieved for the data set containing the highest GSD (5 mm) but also lower spatial resolutions (15 mm) let to useful results what increases the practicability of the approach for larger areas. Traditionally lodging assessment is based on field observations that are neither costefficient nor objective. For that reason, an objective threshold approach was proposed in this study to overcome subjective estimates and improve the accuracy in lodging determination. Compared to manual reference measurement the UAV based lodging percentage provided a very high correlation (R² = 0.96) when applied to breeding trials. As a proof of concept the method was additionally applied to a classical farmer field and let only to a slight overestimation of 2 % compared to reference data. Building on the parameter lodging percentage an approach was developed that allowed the assessment of lodging severity (R² = 0.92), an information that is important to estimate the yield impairment. The assessment of the two lodging parameters was tested on date sets with different ground sampling distances (GSDs). The highest accuracies could be achieved for the data set containing the highest GSD (5 mm) but also lower spatial resolutions (15 mm) let to useful results what increases the practicability of the approach for larger areas. Furthermore, it was investigated that a freely available digital terrain model (DTM) based on airborne LIDAR data can serve as an alternative ground model for the CH retrieval and thus reduces the effort in data acquisition. A comparison of the derived plant traits using the UAV or DTM based ground model showed very high correlations (CH: R² = 0.99, lodging percentage: R² = 0.94). [ABSTRACT FROM AUTHOR]

Copyright of Bornimer Agrartechnische Berichte is the property of Leibniz-Institut fur Agrartechnik und Biookonomie e.V. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)