Estimation Of Biophysical Parameters Research Articles

Fluorescence-based multifunctional light sheet imaging flow cytometry for high-throughput optical interrogation of live cells

Multifunctional light sheet imaging flow cytometry of a large population of live cells at high throughput is challenging and requires new technological advancement. Existing cytometry techniques are limited due to point-based illumination that does not allow volume interrogation and biophysical parameter estimation on the go. Here, we propose a multifunctional (multichannel, multisheet and multicolor) imaging cytometry (M3IC) system that employs vertically-aligned multi-sheet array (VAMSA) illumination for interrogating cells flowing simultaneously through multiple microfluidic channels. We studied cancer cells (volume interrogation with organelle-level resolution and high signal-to-background-ratio(SBR)) at high throughput (~2500 nl/min). M3IC system demonstrates organelle-level resolution with a SBR comparable to that of confocal, especially at low flow rates. In addition, the multicolor imaging capability of the system facilitates multi-organelle investigation, determination of critical biophysical parameters, and drug (Paclitaxel) treatment studies on cancer cells. M3IC system is expected to advance the field of fluorescence microscopy, cell biophysics, disease biology and optical physics.

Estimation of above ground biomass, biophysical and quality parameters of spinach (Spinacia Oleracea L.) using Sentinel-2 to support the supply chain

The estimation of biophysical and biochemical parameters using Sentinel-2 satellite imagery provides crucial information to support agronomic management and logistics for the processing industry, yet this approach has been poorly explored for vegetable crops, such as spinach (Spinacia oleracea L.). For this reason, Sentinel-2 satellite images were used to estimate biophysical and biochemical parameters of open field spinach crops (Above Ground Biomass (AGB), Canopy Nitrogen Content (CNC), Leaf Area Index (LAI), Canopy Chlorophyll Content (CCC), Leaf Dry Matter Content (LDMC), Leaf Nitrogen Content (LNC), Leaf Nitrate Content (LNO3−C) and Leaf Chlorophyll Content (LCC)). Spinach samples were collected in northern Italy in two different growing seasons (2020 – 2021) to measure biophysical and biochemical parameters which were linearly regressed via linear regression k-fold to five vegetation indices retrieved from Sentinel-2 images (MCARI, NDRE, NDVI, NDWI and SR). The AGB estimation models were also validated at field scale using historical data, totally independent from those used for the model calibration, collected by the processing industry between 2018 and 2021. Overall, canopy-level parameters (AGB, LAI, CNC, CCC) were estimated more accurately than leaf-level parameters (LDMC, LNC, LNO3−C, LCC). The highest accuracy was observed for the estimation of the canopy-scale parameter AGB (nRMSE = 9.48 %, R2 = 0.87) using MCARI, while the lowest accuracy was observed for the estimation of the leaf-scale parameter LCC (nRMSE = 29.24 %, R2 = 0.01) using NDWI. At field level, the validation of the AGB estimation models showed the highest performance using SR (nRMSE = 19.69 %, R2 = 0.21). This work demonstrates that using Sentinel-2 satellite images, it is feasible to estimate biophysical and biochemical parameters useful for monitoring the health of spinach crops for both agronomic management and the industrial supply chain.

A deep transfer learning framework for mapping high spatiotemporal resolution LAI

Leaf area index (LAI) is an important variable for characterizing vegetation structure. Contemporary satellite-based LAI products with moderate spatial resolution, such as those derived from the MODIS observations, offer unique opportunities for large-scale monitoring but are insufficient for resolving heterogeneous landscapes. Although high-resolution satellite observations can derive detailed LAI maps, the low revisit frequency and the presence of cloud cover disrupt the temporal continuity of these high-resolution data, thereby leading to the fact that most current LAI inversion models for high spatial resolution data are based on single pixel and date without fully utilizing temporal information. Moreover, LAI estimation models trained solely using satellite products or simulations are also impeded by the inconsistencies between field and satellite LAI exist owing to local atmospheric, soil, and canopy conditions, while in-situ LAI measurements are sparse and insufficient for large-scale missions. To address these challenges, this study proposed a new framework based on deep transfer learning, which includes three key features that contribute to its high performance. Firstly, a Bi-directional Long Short-Term Memory (Bi-LSTM) model is pre-trained using MODIS reflectance and MODIS LAI products to capture the general non-linear relationship between reflectance and LAI and incorporate temporal dependencies as prior information to reduce uncertainties associated with ill-posed inversion problems and noises. Secondly, this pre-trained Bi-LSTM is transferred from satellite to field by fine-tuning with sparse in-situ LAI measurements to overcome issues arising from local inconsistencies. Thirdly, reconstructed Landsat time-series images via fusing MODIS and Landsat reflectance images are used as inputs of the Bi-LSTM to generate high-quality Landsat LAI products at both high spatial and temporal resolutions. To validate the proposed approach, field LAI measurements were collected at nine locations across the contiguous U.S. from 2000 to 2018, including three land cover types: croplands, grasslands, and forest. Quantitative assessments demonstrate that the Bi-LSTM outperforms three benchmarks, including a PROSAIL-based Look-Up Table (LUT) method, a random forest-based LAI retrieval and MODIS LAI (MCD15A3H), exhibiting lower RMSE and higher R2 in most cases. Additionally, the Bi-LSTM predictions yield lower random fluctuations than estimations from the LUT·, random forest and MODIS LAI, indicating the higher robustness of the proposed framework. The findings of this study highlight the value of transfer learning in estimation of vegetation biophysical parameters, which involves pre-training using sufficient existing satellite products to produce a generalized model and transferring knowledge from in-situ measurements to bridge gaps between satellite and field. By leveraging advanced transfer learning techniques and multi-source and multi-scale data, the proposed framework enables the production of long-term LAI maps at fine resolutions, facilitating downstream applications in regions characterized by high spatial heterogeneity.

A computational model to uncover the biophysical underpinnings of neural firing heterogeneity in dissociated hippocampal cultures.

Calcium (Ca2+ ) imaging reveals a variety of correlated firing in cultures of dissociated hippocampal neurons, pinpointing the non-synaptic paracrine release of glutamate as a possible mediator for such firing patterns, although the biophysical underpinnings remain unknown. An intriguing possibility is that extracellular glutamate could bind metabotropic receptors linked with inositol trisphosphate (IP3 ) mediated release of Ca2+ from the endoplasmic reticulum of individual neurons, thereby modulating neural activity in combination with sarco/endoplasmic reticulum Ca2+ transport ATPase (SERCA) and voltage-gated Ca2+ channels (VGCC). However, the possibility that such release may occur in different neuronal compartments and can be inherently stochastic poses challenges in the characterization of such interplay between various Ca2+ channels. Here we deploy biophysical modeling in association with Monte Carlo parameter sampling to characterize such interplay and successfully predict experimentally observed Ca2+ patterns. The results show that the neurotransmitter level at the plasma membrane is the extrinsic source of heterogeneity in somatic Ca2+ transients. Our analysis, in particular, identifies the origin of such heterogeneity to an intrinsic differentiation of hippocampal neurons in terms of multiple cellular properties pertaining to intracellular Ca2+ signaling, such as VGCC, IP3 receptor, and SERCA expression. In the future, the biophysical model and parameter estimation approach used in this study can be upgraded to predict the response of a system of interconnected neurons.

Landsat-7 ETM+, Landsat-8 OLI, and Sentinel-2 MSI Surface Reflectance Cross-Comparison and Harmonization over the Mediterranean Basin Area

In the Mediterranean area, vegetation dynamics and phenology analysed over a long time can have an important role in highlighting changes in land use and cover as well as the effect of climate change. Over the last 30 years, remote sensing has played an essential role in bringing about these changes thanks to many types of observations and techniques. Satellite images are to be considered an important tool to grasp these dynamics and evaluate them in an inexpensive and multidisciplinary way thanks to Landsat and Sentinel satellite constellations. The integration of these tools holds a dual potential: on the one hand, allowing us to obtain a longer historical series of reflectance data, while on the other hand making data available with a higher frequency even within a specific timeframe. The study aims to conduct a comprehensive cross-comparison analysis of long-time-series pixel values in the Mediterranean regions. For this scope comparisons between Landsat-7 (ETM+), Landsat-8 (OLI), and Sentinel-2 (MSI) satellite sensors were conducted based on surface reflectance products. We evaluated these differences using Ordinary Least Squares (OLS) and Major Axis linear regression (RMA) analysis on points extracted from over 15,000 images across the Mediterranean basin area from 2017 to 2020. Minor but consistent differences were noted, necessitating the formulation of suitable adjustment equations to better align Sentinel-2 reflectance values with those of Landsat-7 or Landsat-8. The results of the analysis are compared with the most-used harmonization coefficients proposed in the literature, revealing significant differences. The root-mean-square deviation, the mean difference and the orthogonal distance regression (ODR) slope show an improvement of the parameters for both models used (OLS and RMA) in this study. The discrepancies in reflectance values leads to corresponding variations in the estimation of biophysical parameters, such as NDVI, showing an increase in the ODR slope of 0.3. Despite differences in spatial, spectral, and temporal characteristics, we demonstrate that integration of these datasets is feasible through the application of band-wise regression corrections for a sensitive and heterogeneous area like those of the Mediterranean basin area.

A temperature-controlled cooling system for accurate quantitative post-mortem MRI.

To develop a temperature-controlled cooling system to facilitate accurate quantitative post-mortem MRI and enable scanning of unfixed tissue. A water cooling system was built and integrated with a 7T scanner to minimize temperature drift during MRI scans. The system was optimized for operational convenience and rapid deployment to ensure efficient workflow, which is critical for scanning unfixed post-mortem samples. The performance of the system was evaluated using a 7-h diffusion MRI protocol at 7T with a porcine tissue sample. Quantitative T1 , T2 , and ADC maps were interspersed with the diffusion scans at seven different time points to investigate the temperature dependence of MRI tissue parameters. The impact of temperature changes on biophysical model fitting of diffusion MRI data was investigated using simulation. Tissue T1 , T2 , and ADC values remained stable throughout the diffusion MRI scan using the developed cooling system, but varied substantially using a conventional scan setup without temperature control. The cooling system enabled accurate estimation of biophysical model parameters by stabilizing the tissue temperature throughout the diffusion scan, while the conventional setup showed evidence of significantly biased estimation. A temperature-controlled cooling system was developed to tackle the challenge of heating in post-mortem imaging, which shows potential to improve the accuracy and reliability of quantitative post-mortem imaging and enables long scans of unfixed tissue.

Measuring cardiomyocyte cellular characteristics in cardiac hypertrophy using diffusion-weighted MRI.

This paper presents a hierarchical modeling approach for estimating cardiomyocyte major and minor diameters and intracellular volume fraction (ICV) using diffusion-weighted MRI (DWI) data in ex vivo mouse hearts. DWI data were acquired on two healthy controls and two hearts 3 weeks post transverse aortic constriction (TAC) using a bespoke diffusion scheme with multiple diffusion times ( ), q-shells and diffusion encoding directions. Firstly, a bi-exponential tensor model was fitted separately at each diffusion time to disentangle the dependence on diffusion times from diffusion weightings, that is, b-values. The slow-diffusing component was attributed to the restricted diffusion inside cardiomyocytes. ICV was then extrapolated at using linear regression. Secondly, given the secondary and the tertiary diffusion eigenvalue measurements for the slow-diffusing component obtained at different diffusion times, major and minor diameters were estimated assuming a cylinder model with an elliptical cross-section (ECS). High-resolution three-dimensional synchrotron X-ray imaging (SRI) data from the same specimen was utilized to evaluate the biophysical parameters. Estimated parameters using DWI data were (control 1/control 2 vs. TAC 1/TAC 2): major diameter-17.4 m/18.0 m versus 19.2 m/19.0 m; minor diameter-10.2 m/9.4 m versus 12.8 m/13.4 m; and ICV-62%/62% versus 68%/47%. These findings were consistent with SRI measurements. The proposed method allowed for accurate estimation of biophysical parameters suggesting cardiomyocyte diameters as sensitive biomarkers of hypertrophy in the heart.

Development of the grass LAI and CCC remote sensing-based models and their transferability using sentinel-2 data in heterogeneous grasslands

ABSTRACT Estimation of biophysical variables such as leaf area index (LAI) and canopy chlorophyll content (CCC) at high spatiotemporal resolution is important for managing natural and heterogeneous environments. However, accurate estimation of biophysical variables particularly over heterogeneous environments remains a challenge. The objective of the study was to develop locally parameterized grass LAI and CCC empirical models using the Sentinel-2 variables combined with the Stepwise multiple linear regression (SMLR) and Random forest (RF) at the Golden Gate Highlands National Park (GGHNP) and Marakele National Park (MNP) in South Africa. Results showed that in MNP, SMLR yielded better LAI estimation with root mean squared error (RMSE) of 0.67 m2.m−2 and mean adjusted error (MAE) of 0.54, explaining 48% of LAI variability, when bands and indices are combined. In contrast, RF gave better CCC estimation i.e. RMSE and MAE of 17.08 µg.cm−2 and 13.18 respectively, explaining about 40% of CCC variability with Sentinel-2 bands only. In GGHNP, the RF models provided the best estimates of both LAI and CCC compared to SMLR models. Furthermore, the CCC and LAI estimation models of GGHNP showed improved model accuracies when 50% and 75% of the MNP field samples were transferred to the GGHNP models. In contrast, the CCC and LAI estimation models of MNP showed a decline in model performance across all scenarios where the GGHNP field samples were transferred to the MNP models. These findings have significant implications for the development of locally parameterized types of models that can provide improved and consistent site-specific accurate estimates of grass biophysical parameters over heterogeneous environments.

Estimation of shrub willow biophysical parameters across time and space from Sentinel-2 and unmanned aerial system (UAS) data

Shrub willow can be used as a perennial energy crop to produce biomass for biofuels, bioproducts, and bioenergy to help address environmental issues. Leaf chlorophyll content (LCC), leaf area index (LAI), and canopy chlorophyll content (CCC), which are closely related to vegetation health status, provide valuable information to assess willow vigor and crop management activities. We developed models for estimating LCC, LAI, and CCC from Sentinel-2 and unmanned aerial system (UAS) data using a number of vegetation indices (VIs) and applying four analytical tools: regression analysis, partial least squares regression (PLSR), random forest (RF), and neural networks (NNs). We investigated twenty VIs using regression analysis, finding the red-edge normalized difference vegetation index (NDVIre) as the optimal VI based on predictive performance and so this was included as an input variable for the PLSR, RF, and NN methods. For RF and NN models, sensitivity analysis was implemented to help tune hyperparameters and provide information to guide future studies. Results showed that the best averaged performance of Sentinel-2 and UAS data for LCC, LAI, and CCC (normalized root mean square error (NRMSE) = 9%, 12%, and 10%) of the same site in the same year was derived from models based on the NN algorithm using blue (B), green (G), red (R), red-edge (RE), and near-infrared (NIR) bands. In order to test model transferability, we collected UAS and Sentinel-2 data across different years and sites. Based on NRMSE, NN models using B, G, R, RE, and NIR bands provided the best averaged predictive performance for LCC estimation (16%) and the regression modeling using NDVIre performed best for LAI (21%) and CCC (13%) estimation for both Sentinel-2 and UAS data. Moreover, CCC estimation had smaller NRMSE values than LCC and LAI estimation for both Sentinel-2 and UAS data. Based on this study, we found that UAS data has the potential to complement Sentinel-2 data by mitigating limitations caused by temporal resolution and cloud cover. We also recommend use of the CCC parameter to evaluate shrub willow health status and perform time-series monitoring across time and space.

In vitro and in silico approaches to engineering three-dimensional biological tissues and organoids

<i>In vitro</i> and <i>in silico</i> approaches to engineering three-dimensional biological tissues and organoids

Structural attributes estimation in a natural tropical forest fragment using very high-resolution imagery from unmanned aircraft systems

Structural attributes are fundamental biophysical parameters of forest, useful for ecological and environmental monitoring and planning. Canopy height is an important input for the estimation of several biophysical parameters as aboveground biomass and carbon stock, and can be related with forest degradation, deforestation, and emission reduction. Thus, an accurate canopy height estimation is a crucial issue in climate change studies and REDD+ initiatives. VHR imagery from unmanned aircraft systems has been studied as a low cost mean for canopy height estimation at local scales, but the accuracy in the estimation is a factor that determines its utility. We evaluated the ability of VHR imagery from unmanned aircraft systems to derive structural attributes, specifically tree-crown area and height, in a natural tropical forest fragment located in the foothills of the Andes Mountains, in the humid tropical forests of the region known as Biogeographic Chocó, South America. The region is one of the most biodiverse areas of the world and has a high level of endemism, but it is also at higher risk of natural-resource loss. We used a structure from motion approach to derive canopy height models of the forest fragment, and we applied mean-shift algorithms to identify single tree crowns. The accuracy assessment was performed using reference data derived from field campaigns and visually interpretation of VHR imagery. The estimated root-mean-square error of the population of vertical errors for the canopy height model was 3.6 m. The total accuracy for delineating tree crowns was 73.9%. We found that using VHR imagery, specific trees and canopy gaps can be identified and easily monitored, which is an important step in conservation programs. We also discuss the usefulness of these findings in the context of fragmented forests and the tradeoffs between the price of a LIDAR system and the accuracy of this approach.

Combining Spectral, Spatial-Contextual, and Structural Information in Multispectral UAV Data for Spruce Crown Delineation

Precise delineation of individual tree crowns is critical for accurate forest biophysical parameter estimation, species classification, and ecosystem modelling. Multispectral optical remote sensors mounted on low-flying unmanned aerial vehicles (UAVs) can rapidly collect very-high-resolution (VHR) photogrammetric optical data that contain the spectral, spatial, and structural information of trees. State-of-the-art tree crown delineation approaches rely mostly on spectral information and underexploit the spatial-contextual and structural information in VHR photogrammetric multispectral data, resulting in crown delineation errors. Here, we propose the spectral, spatial-contextual, and structural information-based individual tree crown delineation (S3-ITD) method, which accurately delineates individual spruce crowns by minimizing the undesirable effects due to intracrown spectral variance and nonuniform illumination/shadowing in VHR multispectral data. We evaluate the performance of the S3-ITD crown delineation method over a white spruce forest in Quebec, Canada. The highest mean intersection over union (IoU) index of 0.83, and the lowest mean crown-area difference (CAD) of 0.14 m2, proves the superior crown delineation performance of the S3-ITD method over state-of-the-art methods. The reduction in error by 2.4 cm and 1.0 cm for the allometrically derived diameter at breast height (DBH) estimates compared with those from the WS-ITD and the BF-ITD approaches, respectively, demonstrates the effectiveness of the S3-ITD method to accurately estimate biophysical parameters.

Biophysical parameter estimation of crops from polarimetric synthetic aperture radar imagery with data-driven polynomial chaos expansion and global sensitivity analysis

• Polynomial Chaos Expansion regression is suitable for estimation of crop biophysical parameters. • Correlated input vectors prevent reliable Global Sensitivity Analysis with Sobol’s method. • Relationship between polynomial coefficients and Sobol sensitivity indices is an advantage. • Interactions between features affect regression of biophysical parameters in different level. Data-driven machine learning regression methods are easy to implement and applicable to a wide-range of data in biophysical parameter estimation and have become a common approach in the remote sensing field. Among the regression methods, polynomial chaos expansion (PCE) is one of the reliable and interesting ones due to its tight relationship with uncertainty quantification. One of the advantages of PCE is that global sensitivity analysis (GSA) with Sobol’s method can be analytically computed from polynomial coefficients if the input space is statistically independent. However, most of the phenomena include dependent features either statistically or physically. Though the physical independence is provided between inputs, they must be statistically uncorrelated. Therefore, an independent and uncorrelated input space must be created before the regression analysis. In this paper, we performed PCE-based regression analysis for the estimation of biophysical parameters of crops. The study was conducted in the experimental fields of field pea, barley, canola, and oat of the AgriSAR2009 campaign. The input parameters of the regression model were formed by creating polarimetric features derived from RADARSAT-2 imagery. The estimated biophysical parameters were based on the discrete in situ measurements of leaf area index (LAI) and normalized difference vegetation index (NDVI), scattered semi-randomly in each crop field. We implemented neighbourhood component analysis (NCA) to create an independent and uncorrelated input space by eliminating correlations. Finally, we investigated the importance of features, which drive the PCE-based regression models applying GSA with Sobol’s method. Besides the individual effects of each feature, their interactions were found significant.

Combining Sentinel-1 and -3 Imagery for Retrievals of Regional Multitemporal Biophysical Parameters Under a Deep Learning Framework

Regions with excessive cloud cover lead to limited feasibility of applying optical images to monitor crop growth. In this study, we built an upsampling moving window network for regional crop growth monitoring (UMRCGM) model to estimate the two key biophysical parameters (BPs), leaf area index (LAI) and canopy chlorophyll content (CCC) during the main growth period of winter wheat by using Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-3 optical images. Sentinel-1 imagery is unaffected by cloudy weather and Sentinel-3 imagery has a wide width and short revisit period, the organic combination of the two will greatly improve the ability to monitor crop growth at a regional scale. The impact of two different types of SAR information (intensity and polarization) on the estimation of the two BPs was further analyzed. The UMRCGM model optimized the correspondence between inputs and outputs, it had more accurate LAI and CCC estimates compared with the three classical machine learning models, and had the highest accuracy at the green-up stage of winter wheat, followed by the jointing stage and the heading-filling stage, and the lowest accuracy was found at the milk maturity stage. The estimation accuracies of CCC were slightly higher than that of LAI for the first three growth stages of winter wheat, while lower than that of LAI for the milk maturity stage. This study proposes a new method for regional BPs (especially for CCC) estimation by combining SAR and optical imagery with large differences in spatial resolution under a deep learning framework.

Application of the Trace Coherence to HH-VV PolInSAR TanDEM-X Data for Vegetation Height Estimation

This article investigates, for the first time, the inclusion of the operator Trace Coherence (TrCoh) in polarimetric and interferometric synthetic aperture radar (SAR) methodologies for the estimation of biophysical parameters of vegetation. A modified inversion algorithm based on the well-known Random Volume over Ground (RVoG) model, which employs the TrCoh, is described and evaluated. In this regard, a different set of coherence extrema is used as input for the retrieval stage. In addition, the proposed methodology improves the inversion algorithm by employing analytical solutions rather than approximations. Validation is carried out exploiting single-pass HH-VV bistatic TanDEM-X data, together with reference data acquired over a paddy rice area in Spain. The added value of the TrCoh and the convenience of the use of analytical solutions are assessed by comparing with the conventional polarimetric SAR interferometry (PolInSAR) algorithm. Results demonstrate that the modified proposed methodology is computationally more effective than current methods on this dataset. For the same scene, the steps required for inversion are computed in 6 min with the conventional method, while it only takes 6 s with the proposed approach. Moreover, vegetation height estimates exhibit a higher accuracy with the proposed method in all fields under evaluation. The root-mean-squared error reached with the modified method improves by 7 cm with respect to the conventional algorithm.

The Expanding Horizon of Light Sheet Technology

Seldom, do we come across a technology that advances multiple research disciplines across science and engineering. One such technology is light sheet that promises to take scientific investigation to the next level. The existing technology, predominantly based on point-focusing has reached a saturation limit, in terms of speed, limited field-of-view and lack of biophysical parameter estimation. Moreover, current technology is complex and needs human intervention. Light sheet techniques based on sheet-illumination expand our abilities for high throughput interrogation of a large pool of live biological specimens with near diffraction-limited resolution and an order increase in field-of-view. The outlook of research community has changed dramatically over the last decade that has seen an increased use of light sheet technology. Light sheet technique has penetrated both biological and physical sciences with its impact on microscopy, cytometry, nanolithography, beam-shaping, plasma physics and optical manipulation. Eventually, the technique will influence other disciplines and may give rise to new research fields.

Estimating Crop Biophysical Parameters Using Machine Learning Algorithms and Sentinel-2 Imagery

Global food security is critical to eliminating hunger and malnutrition. In the changing climate, farmers in developing countries must adopt technologies and farming practices such as precision agriculture (PA). PA-based approaches enable farmers to cope with frequent and intensified droughts and heatwaves, optimising yields, increasing efficiencies, and reducing operational costs. Biophysical parameters such as Leaf Area Index (LAI), Leaf Chlorophyll Content (LCab), and Canopy Chlorophyll Content (CCC) are essential for characterising field-level spatial variability and thus are necessary for enabling variable rate application technologies, precision irrigation, and crop monitoring. Moreover, robust machine learning algorithms offer prospects for improving the estimation of biophysical parameters due to their capability to deal with non-linear data, small samples, and noisy variables. This study compared the predictive performance of sparse Partial Least Squares (sPLS), Random Forest (RF), and Gradient Boosting Machines (GBM) for estimating LAI, LCab, and CCC with Sentinel-2 imagery in Bothaville, South Africa and identified, using variable importance measures, the most influential bands for estimating crop biophysical parameters. The results showed that RF was superior in estimating all three biophysical parameters, followed by GBM which was better in estimating LAI and CCC, but not LCab, where sPLS was relatively better. Since all biophysical parameters could be achieved with RF, it can be considered a good contender for operationalisation. Overall, the findings in this study are significant for future biophysical product development using RF to reduce reliance on many algorithms for specific parameters, thus facilitating the rapid extraction of actionable information to support PA and crop monitoring activities.

Diffusional Kurtosis Imaging in the Diffusion Imaging in Python Project.

Diffusion-weighted magnetic resonance imaging (dMRI) measurements and models provide information about brain connectivity and are sensitive to the physical properties of tissue microstructure. Diffusional Kurtosis Imaging (DKI) quantifies the degree of non-Gaussian diffusion in biological tissue from dMRI. These estimates are of interest because they were shown to be more sensitive to microstructural alterations in health and diseases than measures based on the total anisotropy of diffusion which are highly confounded by tissue dispersion and fiber crossings. In this work, we implemented DKI in the Diffusion in Python (DIPY) project—a large collaborative open-source project which aims to provide well-tested, well-documented and comprehensive implementation of different dMRI techniques. We demonstrate the functionality of our methods in numerical simulations with known ground truth parameters and in openly available datasets. A particular strength of our DKI implementations is that it pursues several extensions of the model that connect it explicitly with microstructural models and the reconstruction of 3D white matter fiber bundles (tractography). For instance, our implementations include DKI-based microstructural models that allow the estimation of biophysical parameters, such as axonal water fraction. Moreover, we illustrate how DKI provides more general characterization of non-Gaussian diffusion compatible with complex white matter fiber architectures and gray matter, and we include a novel mean kurtosis index that is invariant to the confounding effects due to tissue dispersion. In summary, DKI in DIPY provides a well-tested, well-documented and comprehensive reference implementation for DKI. It provides a platform for wider use of DKI in research on brain disorders and in cognitive neuroscience.

Deep Learning-Based Estimation of Crop Biophysical Parameters Using Multi-Source and Multi-Temporal Remote Sensing Observations

Remote sensing data are considered as one of the primary data sources for precise agriculture. Several studies have demonstrated the excellent capability of radar and optical imagery for crop mapping and biophysical parameter estimation. This paper aims at modeling the crop biophysical parameters, e.g., Leaf Area Index (LAI) and biomass, using a combination of radar and optical Earth observations. We extracted several radar features from polarimetric Synthetic Aperture Radar (SAR) data and Vegetation Indices (VIs) from optical images to model crops’ LAI and dry biomass. Then, the mutual correlations between these features and Random Forest feature importance were calculated. We considered two scenarios to estimate crop parameters. First, Machine Learning (ML) algorithms, e.g., Support Vector Regression (SVR), Random Forest (RF), Gradient Boosting (GB), and Extreme Gradient Boosting (XGB), were utilized to estimate two crop biophysical parameters. To this end, crops’ dry biomass and LAI were estimated using three input data; (1) SAR polarimetric features; (2) spectral VIs; (3) integrating both SAR and optical features. Second, a deep artificial neural network was created. These input data were fed to the mentioned algorithms and evaluated using the in-situ measurements. These observations of three cash crops, including soybean, corn, and canola, have been collected over Manitoba, Canada, during the Soil Moisture Active Validation Experimental 2012 (SMAPVEX-12) campaign. The results showed that GB and XGB have great potential in parameter estimation and remarkably improved accuracy. Our results also demonstrated a significant improvement in the dry biomass and LAI estimation compared to the previous studies. For LAI, the validation Root Mean Square Error (RMSE) was reported as 0.557 m2/m2 for canola using GB, and 0.298 m2/m2 for corn using GB, 0.233 m2/m2 for soybean using XGB. RMSE was reported for dry biomass as 26.29 g/m2 for canola utilizing SVR, 57.97 g/m2 for corn using RF, and 5.00 g/m2 for soybean using GB. The results revealed that the deep artificial neural network had a better potential to estimate crop parameters than the ML algorithms.

Inference over radiative transfer models using variational and expectation maximization methods

Earth observation from satellites offers the possibility to monitor our planet with unprecedented accuracy. Radiative transfer models (RTMs) encode the energy transfer through the atmosphere, and are used to model and understand the Earth system, as well as to estimate the parameters that describe the status of the Earth from satellite observations by inverse modeling. However, performing inference over such simulators is a challenging problem. RTMs are nonlinear, non-differentiable and computationally costly codes, which adds a high level of difficulty in inference. In this paper, we introduce two computational techniques to infer not only point estimates of biophysical parameters but also their joint distribution. One of them is based on a variational autoencoder approach and the second one is based on a Monte Carlo Expectation Maximization (MCEM) scheme. We compare and discuss benefits and drawbacks of each approach. We also provide numerical comparisons in synthetic simulations and the real PROSAIL model, a popular RTM that combines land vegetation leaf and canopy modeling. We analyze the performance of the two approaches for modeling and inferring the distribution of three key biophysical parameters for quantifying the terrestrial biosphere.