Lucas Wittstruck

Remotely sensed solar-induced chlorophyll fluorescence (SIF) provides a direct measure of photosynthetic activity, but its interpretation across spatial scales is challenged by radiative transfer processes within leaves and canopies. Here, we evaluated established reflectance and physically based approaches for estimating the fluorescence escape probability from leaf to canopy scale ("σ" _"F" ^"LC" ) for red ("F" _"687" ) and far-red SIF ("F" _"760" ) using high-resolution airborne observations of four structurally diverse crops (sugar beet, winter wheat, potato, and maize) acquired at three times of a day, with SCOPE simulations serving as reference. Far-red "σ" _"F" ^"LC" was robustly estimated using reflectance-based proxies, with NIRvH2 showing the best agreement with SCOPE, whereas estimation in the red "σ" _"F" ^"LC" remained challenging due to strong chlorophyll reabsorption and nonlinear radiative transfer effects, with only the 〖"Rom" 〗_"687" approach showing moderate agreement with the reference. Across spectral regions, "σ" _"F" ^"LC" was primarily controlled by canopy structure and leaf biochemical properties: far-red "σ" _"F" ^"LC" was dominated by structural parameters such as leaf area index and leaf orientation, while red "σ" _"F" ^"LC" was mainly driven by leaf chlorophyll content. The derived estimates further enabled calculation of leaf-level fluorescence quantum efficiency ("Φ" _"F" ^"leaf" ), revealing distinct spatial and diurnal patterns associated with canopy structure and physiological regulation. These findings demonstrate that wavelength- and canopy-specific scaling approaches are essential for reliably linking canopy-level SIF observations to leaf-level physiological processes and provide practical guidance for interpreting SIF across observational scales, from tower and airborne measurements to current and upcoming satellite missions such as ESA’s FLuorescence EXplorer (FLEX).

Earth observation missions such as Sentinel and Landsat support the large-scale identification of agricultural crops by providing free radar and multispectral satellite images. The extraction of representative image information as well as the combination of different image sources for improved feature selection still represent a major challenge in the field of remote sensing. In this paper, we propose a novel three-dimensional (3D) deep learning U-Net model to fuse multi-level image features from multispectral and synthetic aperture radar (SAR) time series data for seasonal crop-type mapping at a regional scale. For this purpose, we used a dual-stream U-Net with a 3D squeeze-and-excitation fusion module applied at multiple stages in the network to progressively extract and combine multispectral and SAR image features. Additionally, we introduced a distinctive method for generating patch-based multitemporal multispectral composites by selective image sampling within a 14-day window, prioritizing those with minimal cloud cover. The classification results showed that the proposed network provided the best overall accuracy (94.5%) compared to conventional two-dimensional (2D) and three-dimensional U-Net models (2D: 92.6% and 3D: 94.2%). Our network successfully learned multi-modal dependencies between the multispectral and SAR satellite images, leading to improved field mapping of spectrally similar and heterogeneous classes while mitigating the limitations imposed by persistent cloud coverage. Additionally, the feature representations extracted by the proposed network demonstrated their transferability to a new cropping season, providing a reliable mapping of spatio-temporal crop type patterns.

In order to meet the increasing demand for crops under challenging climate conditions, efficient and sustainable cultivation strategies are becoming essential in agriculture. Targeted herbicide use reduces environmental pollution and effectively controls weeds as a major cause of yield reduction. The key requirement is a reliable weed detection system that is accessible to a wide range of end users. This research paper introduces a self-built, low-cost, multispectral camera system and evaluates it against the high-end MicaSense Altum system. Pixel-based weed and crop classification was performed on UAV datasets collected with both sensors in maize using a U-Net. The training and testing data were generated via an index-based thresholding approach followed by annotation. As a result, the F1-score for the weed class reached 82% on the Altum system and 76% on the low-cost system, with recall values of 75% and 68%, respectively. Misclassifications occurred on the low-cost system images for small weeds and overlaps, with minor oversegmentation. However, with a precision of 90%, the results show great potential for application in automated weed control. The proposed system thereby enables sustainable precision farming for the general public. In future research, its spectral properties, as well as its use on different crops with real-time on-board processing, should be further investigated.

With the advent of high-resolution unmanned aerial vehicle (UAV) data and advancing methods of deep learning, new opportunities have emerged in remote sensing to assess biophysical plant parameters. In this study, we investigated the potential of UAV-borne RGB data and convolutional neural networks (CNNs) to estimate the leaf area index (LAI) of winter wheat during two cropping seasons. In this context, spectral RGB and geometric plant information based on a normalized surface model (nDSM) were used as input variables. The results of the study demonstrated the suitability of optical UAV data and CNNs for LAI estimation of winter wheat at different growth stages and under various lightning conditions. The combination of RGB data and plant structures provided the best overall prediction accuracy (r2 = 0.83) compared to the models with only one input source (RGB: r2 = 0.58, nDSM: r2 = 0.75). Especially the estimation of low and high LAI values was improved using the complementary image information. Moreover, the results showed that the CNN models outperformed two classical machine learning approaches in terms of accuracy.

Pumpkins are economically and nutritionally valuable vegetables with increasing popularity and acreage across Europe. Successful commercialization, however, require detailed pre-harvest information about number and weight of the fruits. To get a non-destructive and cost-effective yield estimation, we developed an image processing methodology for high-resolution RGB data from Unmanned aerial vehicle (UAV) and applied this on a Hokkaido pumpkin farmer’s field in North-western Germany. The methodology was implemented in the programming language Python and comprised several steps, including image pre-processing, pixel-based image classification, classification post-processing for single fruit detection, and fruit size and weight quantification. To derive the weight from two-dimensional imagery, we calculated elliptical spheroids from lengths of diameters and heights. The performance of this processes was evaluated by comparison with manually harvested ground-truth samples and cross-checked for misclassification from randomly selected test objects. Errors in classification and fruit geometry could be successfully reduced based on the described processing steps. Additionally, different lighting conditions, as well as shadows, in the image data could be compensated by the proposed methodology. The results revealed a satisfactory detection of 95% (error rate of 5%) from the field sample, as well as a reliable volume and weight estimation with Pearson’s correlation coefficients of 0.83 and 0.84, respectively, from the described ellipsoid approach. The yield was estimated with 1.51 kg m⁻² corresponding to an average individual fruit weight of 1100 g and an average number of 1.37 pumpkins per m². Moreover, spatial distribution of aggregated fruit densities and weights were calculated to assess in-field optimization potential for agronomic management as demonstrated between a shaded edge compared to the rest of the field. The proposed approach provides the Hokkaido producer useful information for more targeted pre-harvest marketing strategies, since most food retailers request homogeneous lots within prescribed size or weight classes.