Leaf Area Index Time Series Research Articles

Analysis of changes before and after forest fires with LAI, NDVI and ET time series: Focusing on major forest fires in Korea

This study investigates the changes caused by forest fires and the following recovery processes, targeting four forest fire sites in Korea. The time series of two vegetation indices, leaf area index (LAI) and normalized difference vegetation index (NDVI) are investigated along with evapotranspiration (ET) time series for the study objectives. The analysis results show that LAI is most sensitive to burn severity and burned area with its change ranging from 40 % to 70 %, while the changes of NDVI and ET remain 30 % and 20 %, respectively, regardless of forest fire sites. The recovery time from forest fire also varies according to indices: the recovery time is estimated to be about 15 years when considering LAI and NDVI, while just 5 years when considering ET. Overall, LAI seems better to analyze the change in vegetation before and after forest fires. Different vegetation shift patterns after the forest fire are also noticed, mostly from evergreen needleleaf trees to deciduous broadleaf trees. However, it is also found that bad soil fertility condition and artificial afforestation help to maintain the evergreen needleleaf trees after the forest fire.

Predicting time series of vegetation leaf area index across North America based on climate variables for land surface modeling using attention-enhanced LSTM

ABSTRACT Ecosystem process modeling is vital for a broad range of applications. It requires a key metric to characterize vegetation canopies: the leaf area index (LAI). Many land surface models utilize satellite-derived LAI for modeling ecosystem processes. The use of satellite-derived LAI constrains the models for predicting ecosystem processes when observational data are unavailable. Enriching prognostic models for predicting the LAI is favorable to land surface studies for forecasting vegetation-related processes. An attention-enhanced long and short memory (AELSTM) model was developed to predict the vegetation LAI time series based on climatic data. The AELSTM outperformed comparative machine learning models when assessed using satellite and flux tower data. The LAI predicted by AELSTM are temporally and spatially consistent with satellite-derived LAI. The R2 values attained 0.86–0.93 across biomes. AELSTM can be coupled with the land surface models to predict gross primary productivity. Our proposed model was demonstrated to be effective in predicting the LAI time series under different Shared Socioeconomic Pathways in CMIP6. Our study demonstrated that deep learning approaches are capable of modeling and characterizing the spatial and temporal patterns of key vegetation variables such as LAI. Moreover, the study has provided references for vegetation processes in land surface studies.

HiQ-LAI: a high-quality reprocessed MODIS leaf area index dataset with better spatiotemporal consistency from 2000 to 2022

Abstract. Leaf area index (LAI) is a crucial parameter for characterizing vegetation canopy structure and energy absorption capacity. The Moderate Resolution Imaging Spectroradiometer (MODIS) LAI has played a significant role in landmark studies due to its clear theoretical basis, extensive historical time series, extensive validation results, and open accessibility. However, MODIS LAI retrievals are calculated independently for each pixel and a specific day, resulting in high noise levels in the time series and limiting its applications in the regions of optical remote sensing. Reprocessing MODIS LAI predominantly relies on temporal information to achieve smoother LAI profiles with little use of spatial information and may easily ignore genuine LAI anomalies. To address these problems, we designed the spatiotemporal information compositing algorithm (STICA) for the reprocessing of MODIS LAI products. This method integrates information from multiple dimensions, including pixel quality information, spatiotemporal correlation, and the original retrieval, thereby enabling both “reprocessing” and “value-added data” with respect to the existing MODIS LAI products, leading to the development of the high-quality LAI (HiQ-LAI) dataset. Compared with ground measurements, HiQ-LAI shows better performance than the original MODIS product with a root-mean-square error (RMSE) or bias decrease from 0.87 or −0.17 to 0.78 or −0.06, respectively. This is due to the improvement of HiQ-LAI with respect to capturing the seasonality in vegetation phenology and reducing abnormal time-series fluctuations. The time-series stability (TSS) index, which represents temporal stability, indicated that the area with smooth LAI time series expanded from 31.8 % (MODIS) to 78.8 % (HiQ) globally, and this improvement is more obvious in equatorial regions where optical remote sensing cannot usually achieve good performance. We found that HiQ-LAI demonstrates superior continuity and consistency compared with raw MODIS LAI from both spatial and temporal perspectives. We anticipate that the global HiQ-LAI time series, generated using the STICA procedure on the Google Earth Engine (GEE) platform, will substantially enhance support for diverse global LAI time-series applications. The 5 km 8 d HiQ-LAI datasets from 2000 to 2022 are available at https://doi.org/10.5281/zenodo.8296768 (Yan et al., 2023).

Divergent trajectories of future global gross primary productivity and evapotranspiration of terrestrial vegetation in Shared Socioeconomic Pathways

Understanding the future trends of carbon and water fluxes between terrestrial ecosystems and the atmosphere is crucial for predicting Earth's climate dynamics. This study employs an advanced numerical approach to project global gross primary productivity (GPP) and evapotranspiration (ET) from 2001 to 2100 under various climate scenarios based on Shared Socioeconomic Pathways (SSPs). To improve predictions of vegetation dynamics, we introduce a novel model (CoLM-PVPM), an enhancement of the Common Land Model version 2014 (CoLM2014), incorporating a prognostic vegetation phenology model (PVPM). Compared to CoLM2014 that relies on satellite-based leaf area index (LAI) inputs, CoLM-PVPM predicts LAI time series using climate variables. Model validation using historical data from 2001 to 2010 demonstrates PVPM in capturing spatiotemporal variations in satellite LAI. Our modeling results indicate that annual averaged LAI and total GPP increase under SSP1–2.6 but decrease under SSP2–4.5, SSP3–7.0, and SSP5–8.5 by 2100. By comparison, annual total ET consistently increases under all SSP scenarios by 2100. Global annual averaged LAI is highly correlated with annual total GPP in all scenarios, while its correlation with annual total ET weakens in SSP2–4.5, SSP3–7.0, and SSP5–8.5. Global annual total vapor pressure deficit (VPD) and precipitation are highly correlated with annual total ET in all scenarios. As emission levels increase, the negative correlation between annual total VPD and GPP strengthens, while the correlation between annual total precipitation and GPP weakens. This research presents an improved model for predicting terrestrial vegetation processes and underscores the importance of low carbon emission scenarios in maintaining carbon-water balances in specific regions.

Characterisation of grapevine canopy leaf area and inter-row management using Sentinel-2 time series

Accurate data on crop canopy are among the prerequisites for hydrological modelling, environmental assessment, and irrigation management. In this regard, our study concentrated on an in-depth analysis of optical satellite data of Sentinel-2 (S2) time series of the leaf area index (LAI) to characterise canopy development and inter-row management of grapevine fields. Field visits were conducted in the Ouveze-Ventoux area, South Eastern France, for two years (2021 and 2022) to monitor phenology, canopy development, and inter-row management of eleven selected grapevine fields. Regarding the S2-LAI data, the annual dynamic of a typical grapevine canopy leaf area was similar to a double logistic curve. Therefore, an analytic model was adopted to represent the grapevine canopy contribution to the S2-LAI. Part of the parameters of the analytic model were calibrated from the actual grapevine canopy dynamics timing observation from the field visits, while the others were inferred at the field level from the S2-LAI time series. The background signal was generated by directly subtracting the simulated canopy from the S2 LAI time series. Rainfall data were examined to see the possible explanations behind variations in the inter-row grass development. From the background signals, we could group the inter-row management into three classes: grassed, partially grassed, and tilled, which corroborated our findings on the field. To consider the possibility of avoiding field visits, the model was recalibrated on a grapevine field with a clear canopy signal and applied to two fields with different inter-row management. The result showed slight differences among the inter-row signals, which did not prevent the identification of inter-row management, thus indicating that field visits might not be mandatory.

Statistical characterization and exploitation of Synthetic Aperture radar vegetation indexes for the generation of Leaf area Index time series

Statistical characterization and exploitation of Synthetic Aperture radar vegetation indexes for the generation of Leaf area Index time series

A prognostic vegetation phenology model to predict seasonal maximum and time series of global leaf area index using climate variables

Vegetation phenology models provide us with tools for understanding and predicting vegetation responses to a changing climate. Vegetation phenology can be characterized by periodic changes in leaf area index (LAI), which quantifies leaf areas per unit ground surface areas. As an essential variable in land surface studies, LAI is generally used to simulate a range of fundamental vegetation processes and is essential to the simulations of land surface processes and land-atmosphere fluxes. Yet few studies directly provide one key variable required in simulating LAI, the annual seasonal maximum leaf area index (LAISM). There is a need to develop a method for predicting LAISM and allow for simulating daily LAI time series (LAITS). In this study, we developed a Prognostic Vegetation Phenology Model (PVPM) that predicts both LAISM and daily LAITS across biomes at the site and global scales, using climate variables. The method predicts LAISM based on an improved Budyko-like function and then predicts LAITS by integrating a previously developed semi-prognostic model. Experimental results show that PVPM is suitable for simulating vegetation dynamics and provides two parameterization schemes across different biomes at both site and global levels. For different biomes, the model could explain a large variance in satellite-derived LAISM and daily LAITS at the site scale, and well capture the spatial patterns and temporal trends of satellite-derived LAISM and LAITS across the globe. Compared to results obtained from other two process-based climate models (i.e., the GFDL-CM4 and CESM2), PVPM could make predictions on LAITS that match global satellite observations well (r = 0.9 and RMSE < 0.82). This study provides a prognostic vegetation phenology model that can be used in the land surface models to forecast global LAI time series for modeling vegetation processes.

Unravelling the Role of Vegetation Dynamics in the Execution of ArcSWAT Hydrological Modeling for Cumulative Streamflow of a Tibetan Watershed

Monitoring vegetation change and hydrological variation is crucial as they are useful means of appraising the ecological environment and managing water resources in water-resource-sensitive regions. The leaf area index (LAI) describes water consumption in hydrologic processes and is an important vegetation variable for water budgeting in catchments. As part of the Soil and Water Assessment Tool (SWAT), LAI is a significant parameter, which links vegetation dynamics with the hydrological cycle. In the current study, we have aimed to describe the Lhasa River (LR) cumulative streamflow based on simulation scenarios obtained with the SWAT model. After dispensing a heterogeneous LAI time series developed by MODIS NDVI as a source of data at the HRU level (SWAT-synthetic LAI scenario), the study has produced a better representation of LR cumulative streamflow in terms of the selected evaluation criteria, encompassing the SWAT-baseline (SWAT-B scenario)-simulated and SWAT-built-in LAI-influenced (SWAT-LAI scenario) LR cumulative streamflow. The study has revealed a close relationship between the observed and the SWAT-SLAI-scenario-generated LR streamflow, with a similar MK trend for the study time span. The LAI has been found to share a close relationship with LR streamflow, as both the LAI and LR streamflow are found to be influenced by the rainfall received in the Lhasa River Basin (LRB). The study is instrumental in understanding the association between LR streamflow, vegetation change, and the climatic conditions of the Lhasa River Basin (LRB).

Correlation of satellite-based LAI and actual crop yield

The main objective of this article was to investigate the correlation between actual crop yield and Sentinel-2 Leaf Area Index (LAI) for the further possibility of predict model creating. To do so, the following steps have been done. Step 1 – the dataset of actual crop yield was collected for 2364 fields in Ukraine represented with maize, soy, sunflower, winter wheat, winter rapeseed and winter barley. Step 2 – the dataset of Sentinel-2 LAI was collected for 2016-2018 period according to the actual crop yield available. Step 3 – LAI preprocessing (spatial averaging, temporal interpolation/extrapolation to fill the time series gaps, smoothing time series dynamics, temporal averaging). In order to accomplish the process of filling the gaps for the LAI time series, the regular time series dynamics of LAI with a 1-day interval were created using 4 methods: linear interpolation, spline interpolation, LOCF (Last Observation Carried Forward) and ARIMA (AutoRegressive Integrated Moving Average). The time series smoothing process have been accomplish using the local polynomial regression (LOESS) function with different degrees of smoothing. The LAI dynamics preprocessing step did not strongly affect the improvement of the correlation coefficients. Thus, the smoothing process for the time series LAI dynamics at the 0.1 degree of smoothing according to the LOCF and ARIMA gap-filling methods of improved correlation coefficients by 0.01 on average. Step 4 – actual yield values were related to preprocessed satellite-based LAI (correlation of actual yields and LAI). A strong relationship was not indicated (with averaged by vegetation periods correlation coefficient of 0.4 for maize, 0.52 – soy, 0.39 – sunflower, 0.86 – winter barley, 0.54 – winter rapeseed and 0.5 – winter wheat). Since the reliability of obtained correlation coefficients also depends on how many observed data points were in the sample, the hypothesis test of the "significance of the correlation coefficient" has been performed and shows the significance level of p &lt; 0.05 for all crops except winter barley (there is insufficient evidence to conclude that high correlation coefficient of 0.86 for this crop is significant). The average correlation coefficient for all crops is about 0.5 (p &lt; 0.05) which is considered low/moderate. Thus, an attempt to create a linear crop yield prediction model using only Leaf Area Index (LAI) derived from Sentinel-2 will not be effective (based on the cases considered).

A High Spatiotemporal Enhancement Method of Forest Vegetation Leaf Area Index Based on Landsat8 OLI and GF-1 WFV Data

The leaf area index (LAI) is a crucial parameter for analyzing terrestrial ecosystem carbon cycles and global climate change. Obtaining high spatiotemporal resolution forest stand vegetation LAI products over large areas is essential for an accurate understanding of forest ecosystems. This study takes the northwestern part of the Inner Mongolia Autonomous Region (the northern section of the Greater Khingan Mountains) in northern China as the research area. It also generates the LAI time series product of the 8-day and 30 m forest stand vegetation growth period from 2013 to 2017 (from the 121st to the 305th day of each year). The Simulated Annealing-Back Propagation Neural Network (SA-BPNN) model was used to estimate LAI from Landsat8 OLI, and the multi-period GaoFen-1 WideField-View satellite images (GF-1 WFV) and the spatiotemporal adaptive reflectance fusion mode (STARFM) was used to predict high spatiotemporal resolution LAI by combining inversion LAI and Global LAnd Surface Satellite-derived vegetation LAI (GLASS LAI) products. The results showed the following: (1) The SA-BPNN estimation model has relatively high accuracy, with R2 = 0.75 and RMSE = 0.38 for the 2013 LAI estimation model, and R2 = 0.74 and RMSE = 0.17 for the 2016 LAI estimation model. (2) The fused 30 m LAI product has a good correlation with the LAI verification of the measured sample site (R2 = 0.8775) and a high similarity with the GLASS LAI product. (3) The fused 30 m LAI product has a high similarity with the GLASS LAI product, and compared with the GLASS LAI interannual trend line, it accords with the growth trend of plants in the seasons. This study provides a theoretical and technical reference for forest stand vegetation growth period LAI spatiotemporal fusion research based on high-score data, and has an important role in exploring vegetation primary productivity and carbon cycle changes in the future.

Through eagle eyes—the potential of satellite-derived LAI time series to estimate masting events and tree-ring width of European beech

Masting is a well-known phenomenon in forest science in which trees recurrently produce exceptional high seed amounts throughout their lifespan. Occurring simultaneously across wide regions, masting may impact carbon sequestration and carbon cycling of forest ecosystems. To identify masting-induced changes in tree canopies, remote sensing methods may offer a suitable tool, though so far only few studies have used RS methods to investigate the relationship between masting and tree-ring width (TRW). Therefore, we employed a regional network of 19 European beech sites along a precipitation gradient in north-eastern Germany, providing time series of TRW (1961–2017) and categorical masting data (1992–2020). Combined with leaf area index (LAI) from the medium-resolution satellite sensors SPOT-VGT/PROBA-V and MODIS, we assessed the relationship between all three parameters by correlation analysis. Furthermore, we identified common climatic drivers and spatial masting patterns along gradients of water availability. We found negative relationships for both TRW and LAI with masting and a positive correlation for TRW with LAI for SPOT-VGT/PROBA-V data. Contrary, MODIS LAI provided no significant relationships. Water availability did not impact masting occurrence or intensity. The climate correlations showed that masting and TRW are commonly driven by summer climate in June and July, while we found no correlations between climate and LAI. We conclude that medium-resolved SPOT-VGT/PROBA-V LAI is suitable to observe masting but not to estimate TRW. Nonetheless, the results should be thoroughly interpreted in the context of uncertainties of RS measurements and complex interactions of different environmental drivers.

Improving the MODIS leaf area index product for a cropland with the nonlinear autoregressive neural network with eXogenous input model

The leaf area index (LAI) is a crucial descriptive parameter of the dynamic change of ground vegetation. The widely used MODIS LAI product, however, does not satisfy the requirements of regional eco-environment modeling. There is an urgent need to improve the product’s overall accuracy. Under this circumstance, this study proposed an improvement scheme based on the nonlinear autoregressive neural network with eXogenous input (NARXNN) model and the high-quality time series LAI inversion result. Case studies were implemented for two seasons a year croplands in Wuzhi, Xinzheng, and Xiangcheng in Henan province. This research acquired 46 periods of the NARXNN model-improved LAI, which went through rigid in situ LAI validation. The in situ measured LAI by LAI-2000 was used to validate the accuracy of NARXNN-enhanced LAI data. The R2 values of the improved LAI of the three research areas are 0.54, 0.41, and 0.51, while the RMSE decreased by 0.07, 0.1, and 0.03, and the bias also decreased to a certain extent. Direct validation using the in situ measured LAI demonstrates that the NARXNN model-enhanced LAI data were more accurate and had a lower bias than MCD15A2H. A comparison of the time series change indicates that the NARXNN-enhanced LAI shows a smoother bimodal change trend and is more conformed to the actual cropland growth than the original MODIS product. The results indicated that the NARXNN neural network further increased the accuracy of the MODIS product and has a particular practical value in future research.

Exploring the Potential of Gaofen-1/6 for Crop Monitoring: Generating Daily Decametric-Resolution Leaf Area Index Time Series

High spatiotemporal resolution time series of leaf area index (LAI) are essential for monitoring crop dynamics and validating coarse-resolution LAI products. The optical satellite sensors at decametric-resolution have historically suffered from a long revisit cycle and cloud contamination issues that hampered the acquisition of frequent and high-quality observations. The 16-m/4-day resolution of the new generation Gaofen-1 (GF-1) and Gaofen-6 (GF-6) satellites provide an unprecedented opportunity to address these limitations. Here we developed an effective strategy to generate daily 16-m LAI maps combing GF-1/6 data and ground LAINet measurements. All high-quality GF-1/6 observations were utilized first to derive smoothed time series of vegetation indices (VIs). Second, a random forest regression (RF-r) model was trained to link the VIs with corresponding field LAI measurements. The trained RF-r was finally employed to generate the LAI maps. Results demonstrated the reliability of the reconstructed daily VIs (relative error < 1%) and the derived LAI time series, which greatly benefited from GF-1/6 high frequency observations. The direct comparison with field LAI measurements by LAI-2200/LI-3000 showed the good performance of retrieved LAI maps, with Bias, RMSE and R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> of 0.05, 0.59 and 0.75, respectively. The LAI time series well captured the spatiotemporal variation of crop growth. Furthermore, the continuous GF-1/6 LAI maps outperformed Sentinel-2 LAI estimates both in terms of temporal frequency and accuracy. Our study indicates the potential of GF-1/6 to generate continuous decametric-resolution LAI maps for fine-scale agricultural monitoring.

Improving the Quality of MODIS LAI Products by Exploiting Spatiotemporal Correlation Information

The Moderate Resolution Imaging Spectroradiometer (MODIS) Leaf Area Index (LAI) product is critical for global terrestrial carbon monitoring and ecosystem modeling. However, MODIS LAI is calculated on a pixel-by-pixel and day-by-day basis without using spatial or temporal correlation information, which leads to its high sensitivity of LAI to uncertainties in observed reflectance resulting in an increased noise level in time series. While exploiting prior knowledge is a common practice to fill gaps in observations, little research has been conducted on reducing noisy fluctuations and improving the overall quality of the MODIS LAI product. To address this issue, we proposed a Spatio-Temporal Information Composition Algorithm (STICA), which directly introduces prior Spatio-temporal correlation and Multiple Quality Assessment (MQA) information into the existing MODIS LAI product. STICA reduces the noise level and improves the quality of the product while maintaining the original physically-based (Radiative Transfer Model, RTM) LAI production process. In our analysis, the R2 increased from 0.79 to 0.81, and the RMSE decreased from 0.81 to 0.68 compared to the ground-based LAI reference. The improvement was more pronounced with the degradation of the data quality. STICA reduced noisy fluctuations in the LAI time series to varying degrees among eight biome types. In the Amazon Forest, STICA significantly improved the time-series stability of LAI. Moreover, STICA can effectively eliminate abnormal declines in time series and correct for extreme outliers in LAI. We expect that the MODIS LAI Reanalyzed product generated by this method will better support the application of high-quality LAI datasets.

Yield estimation of Lycium barbarum L. based on the WOFOST model

Previous research about crop growth simulation and yield prediction mainly focused on annual crops with very few such studies relating to perennial fruit tree crops. In this study, field experiments were conducted in different growth periods of Lycium barbarum L. in Gansu province, China to determine and improve the initial WOFOST model parameters with combination of the time-series leaf area index (LAI) obtained from Sentinel-2 satellite and predict yields for L. barbarum shrubs at a field scale for summer fruit (SF) and autumn fruit (AF). The results showed that the performance of initial parameters established by previous research and partial measured data was relatively poor, with a relative error (RE) of 20.95% for annual yield. The simulation after model parameter calibration significantly improved model prediction accuracy. The predicted SF was 2588 kg/ha and AF was 601 kg/ha with a RE of -5.51%. This study provided a strategy to improve modelled yield for fruit tree crops through utilization of remote sensed and field measured data in model parameter calibration, which on the other hand provides useful information for regional development planning and crops marketing.

Estimation of Vegetation Leaf-Area-Index Dynamics from Multiple Satellite Products through Deep-Learning Method

A high-quality leaf-area index (LAI) is important for land surface process modeling and vegetation growth monitoring. Although multiple satellite LAI products have been generated, they usually show spatio-temporal discontinuities and are sometimes inconsistent with vegetation growth patterns. A deep-learning model was proposed to retrieve time-series LAIs from multiple satellite data in this paper. The fusion of three global LAI products (i.e., VIIRS, GLASS, and MODIS LAI) was first carried out through a double logistic function (DLF). Then, the DLF LAI, together with MODIS reflectance (MOD09A1) data, served as the training samples of the deep-learning long short-term memory (LSTM) model for the sequential LAI estimations. In addition, the LSTM models trained by a single LAI product were considered as indirect references for the further evaluation of our proposed approach. The validation results showed that our proposed LSTMfusion LAI provided the best performance (R2 = 0.83, RMSE = 0.82) when compared to LSTMGLASS (R2 = 0.79, RMSE = 0.93), LSTMMODIS (R2 = 0.78, RMSE = 1.25), LSTMVIIRS (R2 = 0.70, RMSE = 0.94), GLASS (R2 = 0.68, RMSE = 1.05), MODIS (R2 = 0.26, RMSE = 1.75), VIIRS (R2 = 0.44, RMSE = 1.37) and DLF LAI (R2 = 0.67, RMSE = 0.98). A temporal comparison among LSTMfusion and three LAI products demonstrated that the LSTMfusion model efficiently generated a time-series LAI that was smoother and more continuous than the VIIRS and MODIS LAIs. At the crop peak growth stage, the LSTMfusion LAI values were closer to the reference maps than the GLASS LAI. Furthermore, our proposed method was proved to be effective and robust in maintaining the spatio-temporal continuity of the LAI when noisy reflectance data were used as the LSTM input. These findings highlighted that the DLF method helped to enhance the quality of the original satellite products, and the LSTM model trained by the coupled satellite products can provide reliable and robust estimations of the time-series LAI.

The carbon budget of the managed grasslands of Great Britain – informed by earth observations

Abstract. Grasslands cover around two-thirds of the agricultural land area of Great Britain (GB) and are important reservoirs of organic carbon (C). Direct assessments of the C balance of grasslands require continuous monitoring of C pools and fluxes, which is only possible at a small number of experimental sites. By relying on our quantitative understanding of ecosystem C biogeochemistry we develop models of grassland C dynamics and use them to estimate grassland C balance at various scales. Model-based estimation of the C budget of individual fields and across large domains is made complex by the spatial and temporal variability in climate and soil conditions, as well as in livestock grazing, grass cutting and other management activities. In this context, earth observations (EOs) provide subfield-resolution proxy data on the state of grassland canopies, allowing us to infer information about vegetation management, to apply observational constraints to the simulated ecosystems and, thus, to mitigate the effects of model input data uncertainty. Here, we show the potential of model–data fusion (MDF) methods to provide robust analyses of C dynamics in managed grasslands across GB. We combine EO data and biogeochemical modelling by implementing a probabilistic MDF algorithm to (1) assimilate leaf area index (LAI) times series (Sentinel-2); (2) infer defoliation instances (grazing, cutting); and (3) simulate livestock grazing, grass cutting, and C allocation and C exchanges with the atmosphere. The algorithm uses the inferred information on grazing and cutting to drive the model's C removals-and-returns module, according to which ≈1/3 of C in grazed biomass returns to the soil as manure (other inputs of manure not considered) and C in cut grass is removed from the system (downstream C emissions not considered). Spatial information on soil C stocks is obtained from the SoilGrids dataset. The MDF algorithm was applied for 2017–2018 to generate probabilistic estimates of C pools and fluxes at 1855 fields sampled from across GB. The algorithm was able to effectively assimilate the Sentinel-2-based LAI time series (overlap = 80 %, RMSE = 1.1 m2 m−2, bias = 0.35 m2 m−2) and predict livestock densities per area that correspond with independent agricultural census-based data (r = 0.68, RMSE = 0.45 LU ha−1, bias = −0.06 LU ha−1). The mean total removed biomass across all simulated fields was 6 (±1.8) t DM ha−1 yr−1. The simulated grassland ecosystems were on average C sinks in 2017 and 2018; the net biome exchange (NBE) was -191±81 (2017) and -49±69 gC m−2 yr−1 (2018). Our results show that the 2018 European summer drought reduced the strength of C sinks in GB grasslands and led to a 9-fold increase in the number fields that were annual C sources (NBE &gt; 0) in 2018 (18 % of fields) compared to 2017 (2 % of fields). The field-scale analysis showed that management in the form of timing, intensity and type of defoliation were key determinants of the C balance of managed grasslands, with cut fields acting as weaker C sinks compared to grazed fields. Nevertheless, extreme weather, such as prolonged droughts, can convert grassland C sinks to sources.

Integrating an attention-based deep learning framework and the SAFY-V model for winter wheat yield estimation using time series SAR and optical data

Information on the spatial distribution of yields can be obtained over a large area by using remote sensing (RS) data. Combining Synthetic Aperture Radar (SAR), being sensitive to above ground biomass and soil moisture in all weather conditions, and optical data can improve the usability of RS data and provide a basis for pixel-based crop yield estimation (YE). In this study, an Upscaled Convolutional Gated Recurrent Unit model incorporated an attention mechanism (UpSc-AConvGRU model) was proposed to improve the estimation accuracy of the winter wheat growth parameter, Leaf Area Index (LAI). Gap filling the time series of optical data was done with backscatter coefficients, local incidence angles and polarimetric decomposition information from Sentinel-1 SAR imagery. The time series LAI estimated by the UpSc-AConvGRU model and Vegetation Temperature Condition Index (VTCI) retrieved from Sentinel-3 optical imagery were then used as state variables of the SAFY-V model to estimate winter wheat yield. The results showed that the proposed UpSc-AConvGRU model incorporated the Convolutional Block Attention Module (CBAM) can effectively improve the accuracy of LAI estimation, with RMSEs ranging from 0.413 to 0.699 m2 m2 for LAI estimated within main growth stages (MGSs) of winter wheat. The correlation between estimated LAI and Sentinel-3 retrieved LAI was generally higher at irrigated farmland compared to rain-fed farmland. The estimated LAI was closest to Sentinel-3 retrieved LAI at the green-up and late heading-filling stage of winter wheat, followed by the jointing and early heading-filling stage, and finally the milk maturity stage. There was good agreement between the SAFY-V model estimated and field measured winter wheat yields (R2 = 0.546, RMSE = 0.757 t ha−1), and the estimated yields at the pixel scale in the Guanzhong Plain, PR China were satisfactory. This study combined deep learning and crop growth modeling, proposed a new pixel scale winter wheat YE method.

A general grass growth model for urban green spaces management in tropical regions: A case study with bahiagrass in southeastern Brazil

Urban green spaces (UGS) positively impact the population, providing essential ecosystem services and improving public health. Urban vegetation management needs to optimize mowing process costs and reducing impacts on the natural ecosystem. Thus, we implemented a general grass growth model suitable for UGS management in tropical areas, focused on lawns, public parks and squares, roadsides, and around waterways. The model incorporates local edaphoclimatic conditions to simulates the daily dynamics of leaf area index (LAI), biomass, evapotranspiration, and soil water content, going under mowing processes or not, with spatialization capability which might be integrated within geographic information system (GIS) environments. A case study assessing bahiagrass (Paspalum notatum Flüggé) vegetation species in São Carlos, southeastern Brazil, is presented, considering two scenarios to demonstrate the spatial capabilities of the model: (i) UGS as a single area, and (ii) several areas independently. For model validation, vegetation indices calculated based on data from an unmanned aerial vehicle (UAV) and CubeSat imagery (PlanetScope) were used to retrieve LAI time series, calibrated with spectral signatures from leaf ground sampling. For performance analysis, LAI time series from the model and LAI retrieved from both sensors were compared via determination coefficient (R2) and root mean square error (RMSE). Our findings suggest that the proposed model is accurate, and due to its spatialization capability and integration with a GIS, its application may help government administrations to optimize UGS mowing processes.

Remote Prediction of Oilseed Rape Yield via Gaofen-1 Images and a Crop Model

The fast and accurate prediction of crop yield at the regional scale is of great significance to food policies or trade. In this study, a new model is developed to predict the yield of oilseed rape from high-resolution remote sensing images. In order to derive this model, the ground experiment and remote sensing data analysis are carried out successively. In the ground experiment, the leaf area index (LAI) of four growing stages are measured, and a regression model is established to predict yield from ground LAI. In the remote sensing analysis, a new model is built to predict ground LAI from Gaofen-1 images where the simple ratio vegetation index at the bolting stage and the VARIgreen vegetation index at the flowering stage are used. The WOFOSTWOrld FOod STudy (WOFOST) crop model is used to generate time-series ground LAI from discontinuous ground LAI, which is calibrated coarsely with the MODerate resolution imaging spectroradiometer LAI product and finely with the ground-measured data. By combining the two conclusive formulas, an estimation model is built from Gaofen-1 images to the yield of oilseed rape. The effectiveness of the proposed model is verified in Wuxue City, Hubei Province from 2014 to 2019, with the pyramid bottleneck residual network to extract oilseed rape planting areas, the proposed model to estimate yields, and the China statistical yearbooks for comparison. The validation shows that the prediction error of the proposed algorithm is less than 5.5%, which highlights the feasibility of our method for accurate prediction of the oilseed rape yield in a large area.