Relative Root Mean Square Error Research Articles

Rapidly count crop seedling emergence based on waveform Method(WM) using drone imagery at the early stage

Effectively monitoring seedling emergence is critical to identify missing cotton seedling at early stages, allowing the prompt replenishment of the seedlings to maintain crop yield. However, traditional manual inspections have the limitations with low efficiency, poor timeliness, and large counting errors. Although UAV imagery has been applied in seedling monitoring, there are still chance in cotton seedling monitoring under complex environment conditions. Therefore, there is a urgent need for an efficient, rapid, and low-cost method for monitoring early seedling emergence in cotton crops. This study utilizes RGB images of early seedling emergence captured from an unmanned aerial vehicle (UAV) at a flight height of 10 m and a resolution of 0.33 cm in Shihezi, Xinjiang, on 7 and 12 days after seeding (DAS). The modified Hough transform method is constructed for line detection, and crop rows are subsequently extracted from the lines and masked images. After masking, the waveform is extracted from the excess green index (ExG) greyscale map and smoothed to determine the peaks. Seedlings are counted and located by numbering and positioning the peaks, meanwhile their coordinates and distance determine the number and location of missing seedlings. Images with varying resolutions (ranging from 0.33 to 2.5 cm) and intensity changes (0.8 to 1.2) verify the accuracy and efficiency of the proposed waveform method(WM). The results shown that at 7 DAS, the root mean square error (RMSE) is less than 2.0 plants/row, the relative root mean squared error (RRMSE) is less than 2 %, and the coefficient of determination (R2) is stable at 0.95–0.96 when the resolution is below 1.0 cm. The RMSE, RRMSE and R2 fluctuate more when the resolution is less than 1.0 cm. At 12 DAS, the counting accuracy is stable under different conditions, and the RMSE and RRMSE are distributed smoothly over the range of 1.76–4.39 plants/row and 1.29–5.47 % with different resolutions. The R2 is in the range of 0.88–0.97, RRMSE is 1.90–3.39 % and the RMSE is 1.65–2.90 plants/row under different intensities. The results of cotton seedling counting using the waveform method are less affected by image resolution and intensity changes. Therefore, the proposed WM provides efficient, accurate, and automatic counting for cotton seedlings in response to complex weather conditions. Furthermore, it would give a novel approach to accurately countequally spaced row-sown crops based on UAV images.

Modeling the effects of tropospheric ozone on the growth and yield of global staple crops with DSSAT v4.8.0

Abstract. Elevated surface ozone (O3) concentrations can negatively impact growth and development of crop production by reducing photosynthesis and accelerating leaf senescence. Under unabated climate change, future global O3 concentrations are expected to increase in many regions, adding additional challenges to global agricultural production. Presently, few global process-based crop models consider the effects of O3 stress on crop growth. Here, we incorporated the effects of O3 stress on photosynthesis and leaf senescence into the Decision Support System for Agrotechnology Transfer (DSSAT) crop models for maize, rice, soybean, and wheat. The advanced models reproduced the reported yield declines from observed O3-dose field experiments and O3 exposure responses reported in the literature (O3 relative yield loss RMSE <10 % across all calibrated models). Simulated crop yields decreased as daily O3 concentrations increased above 25 ppb, with average yield losses of 0.16 % to 0.82 % (maize), 0.05 % to 0.63 % (rice), 0.36 % to 0.96 % (soybean), and 0.26 % to 1.23 % (wheat) per ppb O3 increase, depending on the cultivar O3 sensitivity. Increased water deficit stress and elevated CO2 lessen the negative impact of elevated O3 on crop yield, but potential yield gains from CO2 concentration increases may be counteracted by higher O3 concentrations in the future, a potentially important constraint to global change projections for the latest process-based crop models. The improved DSSAT models with O3 representation simulate the effects of O3 stress on crop growth and yield in interaction with other growth factors and can be run in the parallel DSSAT global gridded modeling framework for future studies on O3 impacts under climate change and air pollution scenarios across agroecosystems globally.

Branch architecture quantification of large-scale coniferous forest plots using UAV-LiDAR data

Branch architecture plays an important role in forest physical and ecological processes, greatly affecting forest spatial structure and the accumulation, production and distribution of organic carbon. Very few studies have quantified the branch architecture of large-scale forest plots, due to the lack of high-resolution large-scale three-dimensional data. The emergence of unmanned aerial vehicle-light detecting and ranging (UAV-LiDAR) provides great potential to overcome this limitation. However, due to insufficient quality of UAV-LiDAR data for branch reconstruction, existing algorithms remain tremendously challenging. We propose an effective branch reconstruction algorithm for UAV-LiDAR data to quantify branch architecture. First, individual branches are extracted using a region growth method that is guided by the branch growth direction and local smoothness constraint. Second, incorrect branches are eliminated based on three pieces of branch features, i.e., specific angles between branches at the same whorl, specific height differences between branches at different whorls, and the growth pattern of branches from the stem outward, reaching maximum distances at tips. Finally, branches are reconstructed using polynomial fitting, and branch architecture parameters are extracted based on branch models. The proposed algorithm simplifies branch reconstruction by skipping the separation of photosynthetic and non-photosynthetic components. It also adapts well to UAV-LiDAR point clouds, generating more realistic reconstructions. The algorithm successfully identified non-photosynthetic components in experiments involving 240 trees, including Scots pine, Norway spruce, and Radiata pine. The average overall accuracy for these three species was 0.88, 0.76, and 0.74, respectively. The proposed algorithm was tested for branch reconstruction using UAV-LiDAR data from a two-hectare Larix principis-rupprechtii plot. The accuracy of branch identification and parameter extraction accuracy were evaluated branch by branch based on the individual branches manually identified in terrestrial laser scanning data. Results showed the F-score of branch and stem identification was 0.58 and 1. The relative RMSE of branch length and angle was 36.87% and 18.3%, and ones of stem length and diameter were 1.46% and 6.16%. The proposed algorithm outperformed the well-known reconstruction algorithms, including TreeQSM, AdTree and Laplacian-based algorithms.

Water Quality Modelling with Industrial and Domestic Point Source Pollution : a Study Case of Cikakembang River, Majalaya District

Rapid industrial development is one of the leading causes of environmental degradation. The textile industries and the domestic activities in Majalaya District produce wastewater directly discharged into the Cikakembang River. As a result, the Cikakembang River’s water quality has decreased to the point that the water quality cannot be used for daily needs. This study modeled three main parameters in water quality modelling, namely Dissolved Oxygen (DO), Biological Oxygen Demand (BOD), and Chemical Oxygen Demand (COD). Using MATLAB, the three-water quality governing equations originating from the Advection-Dispersion Equation were solved using the Runge Kutte-4 discretization scheme. The numerical modelling was carried out along 2.36 km of the Cikakembang River. All water quality coefficients, such as the DO Saturation (DOsat), the Reaeration Rate (ka), the Dispersion Coefficient (D), the Deoxygenation Rate (kd), and the Decomposition Rate (kc), for the Cikakembang River were estimated using equations developed by existing studies. The estimation of ka and D coefficients requires hydraulic parameters, which in this study were estimated using the HEC-RAS simulation. Meanwhile, kd and kc values were obtained from the calibration and verification process. The Relative Root Mean Square Error (RRMSE) objective function was used to evaluate the results of water quality modelling at three sampling points. In the calibration process, the resultsof water quality modelling produced RRMSE values for the DO, BOD, and COD parameters of 1.99%, 0.36% and 0.92%, respectively. Meanwhile, for the verification process, the RRMSE values for the DO, BOD, and COD parameters are 1.95%, 1.02% and 1.86%. All water quality parameters produce small RRMSE values in the calibration and verification processes. Hence, the water quality model created has good accuracy and stability.

Assessing the impact of irrigation and nitrogen management on potato performance under varying climate in the state of Florida, USA

Optimizing irrigation and nitrogen (N) fertilizer management in irrigated potato crops grown on sandy soils in subtropical regions such as in northeastern Florida, USA is essential to sustain a high yield and to minimize leaching. N applications in this region typically occur at approximately 25–30 days prior to planting (Npre), at emergence (Neme), and at tuber initiation (Nti). However, recent studies suggest that applying N near planting (Npl) enhances fertilizer N use efficiency (FNUE). We combined experimentation with modeling to assess irrigation and N management options for potato in northeastern Florida. We first aimed to evaluate the DSSAT/CSM-SUBSTOR-Potato model using two-year irrigated field experiments conducted on sandy soils with variable N rates and application timings. CSM-SUBSTOR-Potato accurately simulated aboveground plus tuber dry weight [Relative root mean squared error (RRMSE) = 26.4%, Willmott’s index (d) = 0.98] and N accumulation (RRMSE = 28.6%, d = 0.97). Soil moisture and mineral N were captured well overall, but they were often underestimated due to a water table influence that is currently not considered in DSSAT. Subsequently, CSM-SUBSTOR-Potato was applied to simulate tuber yield, N leaching, and FNUE under scenarios of irrigation scheduling and N-fertilizer application (rate/timing) strategies, focusing on Npre versus Npl aiming to improve resource use efficiency. The simulations indicated that a target of 60% and 70% of the available soil water can be safely used as an irrigation strategy to achieve a high yield, while reducing irrigation water applied and N leached to the environment. Overall Npl increased crop N uptake by 10%, tuber yield by 7%, reduced N leached by 13%, and consequently increasing FNUE by 9%, compared to Npre across the irrigation treatments. Thus, Npl should be preferred in sandy soils and climate-risky subtropical environments, along with Neme and Nti as key timings to synchronize N supply with potato growth.

Design and performance evaluation of a compact thermal and fast neutron spectrometer

Measurement of the space neutron radiation environment has put forward new requirements for the miniaturization and lightweight design of neutron spectrometers. In this paper, a compact broad-spectrum neutron spectrometer was designed, in which the fast neutron detector was based on the EJ-254 scintillator-coupled with SiPMs array, and the thermal and epithermal neutron detectors were based on the NaI(Tl + Li) (NaIL) scintillator coupled with SiPMs array encapsulated in Al and Cd shells, respectively. The overall weight of the neutron spectrometer was only 2.4 kg, and its dimensions were 154 mm × 123 mm × 115 mm. The fast neutron energy spectrum was obtained based on the capture-gated method and the Maximum Likelihood Expectation Maximization (MLEM) unfolding algorithm; the counts of thermal and epithermal neutrons were obtained based on the optimized frequency-domain Pulse Shape Discrimination (PSD) method and cadmium difference method. The proposed neutron spectrometer with all applied methods was tested as a whole system with a252Cf and a241Am–Be source. The spectrum result was compared to an ISO standard source. The accuracy of fast part of 0.5–10 MeV was 5.9% in definition of Relative Root Mean Squared Error (RRMSE). The thermal and epithermal neutron counts were far higher than standard spectrum, and we proved it being effected by laboratory introduced neutron scattering through a simulation, thus the thermal and epithermal flux measurements was believed to be decent. The Figure of Merit (FoM) of the NaIL's PSD neutron gamma discrimination were 2.57 and 2.90 respectively.

Machine Learning Modeling Integrating Experimental Analysis for Predicting Compressive Strength of Concrete Containing Different Industrial Byproducts

This study aimed to develop accurate models for estimating the compressive strength (CS) of concrete using a combination of experimental testing and different machine learning (ML) approaches: baseline regression models, boosting model, bagging model, tree-based ensemble models, and average voting regression (VR). The research utilized an extensive experimental dataset with 14 input variables, including cement, limestone powder, fly ash, granulated glass blast furnace slag, silica fume, rice husk ash, marble powder, brick powder, coarse aggregate, fine aggregate, recycled coarse aggregate, water, superplasticizer, and voids in mineral aggregate. To evaluate the performance of each ML model, five metrics were used: mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), coefficient of determination (R2-score), and relative root mean squared error (RRMSE). The comparative analysis revealed that the VR model exhibited the highest effectiveness, displaying a strong correlation between actual and estimated outcomes. The boosting, bagging, and VR models achieved impressive R2-scores in the range of 86.69%–92.43%, with MAE ranging from 3.87 to 4.87, MSE from 21.74 to 38.37, RMSE from 4.66 to 4.87, and RRMSE between 8% and 11%. Particularly, the VR model outperformed all other models with the highest R2-score (92.43%) and the lowest error rate. The developed models demonstrated excellent generalization and prediction capabilities, providing valuable tools for practitioners, researchers, and designers to efficiently evaluate the CS of concrete. By mitigating environmental vulnerabilities and associated impacts, this research can significantly contribute to enhancing the quality and sustainability of concrete construction practices.

A Novel Framework for Forest Above-Ground Biomass Inversion Using Multi-Source Remote Sensing and Deep Learning

The estimation of forest above-ground biomass (AGB) can be significantly improved by leveraging remote sensing (RS) and deep learning (DL) techniques. In this process, it is crucial to obtain appropriate RS features and develop a suitable model. However, traditional methods such as random forest (RF) feature selection often fail to adequately consider the complex relationships within high-dimensional RS feature spaces. Moreover, challenges related to parameter selection and overfitting inherent in DL models may compromise the accuracy of AGB estimation. Therefore, this study proposes a novel framework based on freely available Sentinel-1 synthetic aperture radar (SAR) and Sentinel-2 optical data. Firstly, we designed new indices through the formula analogous with vegetation index calculation to integrate multidimensional spectral and structural information. Then, leveraging the simplicity of computational principles, a pigeon-inspired optimization algorithm (PIO) was introduced into a bi-directional long short-term memory neural network (PIO-BiLSTM), which achieved the set objective function through repeated iteration and validation to obtain the optimal model parameters. Finally, to verify the framework’s effect, we conducted experiments in two different tree species and compared another seven classical optimization algorithms and machine learning models. The results indicated that the new indices significantly improved the inversion accuracy of all models in both categories, and the PIO-BiLSTM model achieved the highest accuracy (Category-1: R2 = 0.8055, MAE = 8.8475 Mg·ha−1, RMSE = 12.2876 Mg·ha−1, relative RMSE = 18.1715%; Category-2: R2 = 0.7956, MAE = 1.7103 Mg·ha−1, RMSE = 2.2887 Mg·ha−1, relative RMSE = 9.3000%). Compared with existing methods, the proposed framework greatly reduced the labor costs in parameter selection, and its potential uncertainty also decreased by up to 9.0%. Furthermore, the proposed method has a strong generalization ability and is independent of tree species, indicating its great potential for future forest AGB inversion in wider regions with diverse forest types.

Evaluation of Six Data Products of Surface Downward Shortwave Radiation in Tibetan Plateau Region

The quantitative characterization of the thermal conditions in the Tibetan Plateau has long been a focal point of global research. Downward shortwave radiation, as a crucial component, plays an important role in numerous land surface processes while also serving as a significant indicator of the plateau’s thermal state. In order to gain a more comprehensive understanding of the Earth’s radiation budget in the Tibetan Plateau region, this study undertook an evaluation of six radiation products (ISCCP-FH, CERES-SYN, GLASS DSR, Himawari-8, MCD18A1, and ERA5). Two sets of ground measurements (downward shortwave radiation values from 10 CMA sites and 6 sites provided by the National Tibetan Plateau Data Center) in 2015 and 2016 were used as validation data to verify the accuracy of the remote sensing products. The results show that in the Tibetan Plateau region, CERESC products show the highest accuracy among the six data products with a bias (relative bias) of −7.57 W/m2 (3.46%), RMSE (relative RMSE) of 32.77 W/m2 (14.99%), and coefficient of determination of 0.80. Among all products, only the ERA5 products overestimated the value of downward shortwave radiation in the Tibetan Plateau region with a bias (relative bias) of 15.62 W/m2 (7.14%). By employing a spatial resolution upscaling approach, we assessed the influence of varying spatial resolutions on the validation accuracy, with the results indicating minimal impact. Through an analysis of the impact of cloud factors and aerosol factors on the validation accuracy, it is deduced that ERA5, Himawari-8, and MCD18A1 products are significantly influenced by cloud factors, whereas the CERES-SYN product is notably affected by aerosol factors.

Improving retrieval of leaf chlorophyll content from Sentinel-2 and Landsat-7/8 imagery by correcting for canopy structural effects

Accurately estimating leaf chlorophyll content (Chl) at large spatial scales is crucial for monitoring agricultural production and plant photosynthesis. Sentinel-2 and Landsat-7/8 offer the potential to assess Chl with high spatial resolutions using various physically-based, empirical, and hybrid methods, but they still present challenges due to the confounding effects of canopy structure and soil background. The near-infrared reflectance of vegetation (NIRV) has been proposed to characterize canopy structural and soil background effects in sun-induced chlorophyll fluorescence. Therefore, in this study, we developed a novel strategy that incorporates NIRV to minimize canopy structural and soil background effects on Chl retrieval, using bidirectional reflectance factor (BRF) from Sentinel-2 and Landsat-7/8 imagery. We compared Chl estimation using empirical random forest (RF), the physically-based PROSAIL-5B inversion, and a hybrid method using RF to train simulated datasets from PROSAIL-5B. We validated Chl retrieval performance with measured datasets from the National Ecological Observatory Network, covering seven vegetation types. We also compared spatiotemporal Chl variations from Sentinel-2, Landsat-7/8, and MODIS. The results showed that NIRV effectively characterized the canopy structural effect on Chl estimation, associated with leaf area index, average leaf angle, and canopy fraction of senescent leaves. Compared to BRF, correcting BRF by NIRV improved Chl retrieval with RMSE values reduced by 12.2%–27.0% for Sentinel-2, 7.4%–16.4% for Landsat-7, and 6.9%–13.7% for Landsat-8, respectively. This also resulted in a significant increase in R2 values for Sentinel-2 (0.13–0.46), Landsat-7 (0.08–0.19), and Landsat-8 (0.12–0.2), respectively. Sentinel-2 outperformed Landsat-7/8 in Chl estimation, due to the contribution of red edge bands and a higher spatial resolution. Furthermore, the hybrid method performed best for Chl estimation from Sentinel-2 and Landsat-7/8 with relative RMSE values of 17.33%, 20.22%, and 19.23%, respectively. Our hybrid method demonstrated lower model uncertainty with smaller variations of RMSE values across varying biochemical and structural traits and solar and viewing angles, and exhibited more consistent spatiotemporal variations of Chl from Sentinel-2 with phenology compared to Landsat-7/8 and the published MODIS Chl data. Our hybrid method demonstrates significant potential in mitigating canopy structural effects, enhancing Chl retrieval, and facilitating the development of Chl data from various satellite imagery sources.

An Ensemble-Based Model for Specific Humidity Retrieval from Landsat-8 Satellite Data for South Korea

Specific humidity (SH) which means the amount of water vapor in 1 kg of air, is used as an indicator of energy exchange between the atmosphere and the Earth’s surface. SH is typically computed using microwave satellites. However, the spatial resolution of data for microwave satellite is too low. To overcome this disadvantage, we introduced new methods that applied data collected by the Landsat-8 satellite with high spatial resolution (30 m), a meteorological model, and observation data for South Korea in 2016–2017 to 4 machine learning techniques to develop an optimized technique for computing SH. Among the 4 machine learning techniques, the random forest-based method had the highest accuracy, with a coefficient of determination (R) of 0.98, Root Mean Square Error (RMSE) of 0.001, bias of 0, and Relative Root Mean Square Error (RRMSE) of 11.16%. We applied this model to compute land surface SH using data from 2018 to 2019 and found that it had high accuracy (R = 0.927, RMSE = 0.002, bias = 0, RRMSE = 28.35%). Although the data used in this study were limited, the model was able to accurately represent a small region based on an ensemble of satellite and model data, demonstrating its potential to address important issues related to SH measurements from satellites.

Fuzzy C-Means clustering for physical model calibration and 7-day, 10-year low flow estimation in ungaged basins: comparisons to traditional, statistical estimates

In the northeast U.S., resource managers commonly apply 7-day, 10-year (7Q10) low flow estimates for protecting aquatic species in streams. In this paper, the efficacy of process-based hydrologic models is evaluated for estimating 7Q10s compared to the United States Geological Survey's (USGS) widely applied web-application StreamStats, which uses traditional statistical regression equations for estimating extreme flows. To generate the process-based estimates, the USGS's National Hydrologic Modeling (NHM-PRMS) framework (which relies on traditional rainfall-runoff modeling) is applied with 36 years of forcings from the Daymet climate dataset to a representative sample of ninety-four unimpaired gages in the Northeast and Mid-Atlantic U.S. The rainfall-runoff models are calibrated to the measured streamflow at each gage using the recommended NHM-PRMS calibration procedure and evaluated using Kling-Gupta Efficiency (KGE) for daily streamflow estimation. To evaluate the 7Q10 estimates made by the rainfall-runoff models compared to StreamStats, a multitude of error metrics are applied, including median relative bias (cfs/cfs), Root Mean Square Error (RMSE) (cfs), Relative RMSE (RRMSE) (cfs/cfs), and Unit-Area RMSE (UA-RMSE) (cfs/mi2). The calibrated rainfall-runoff models display both improved daily streamflow estimation (median KGE improving from 0.30 to 0.52) and 7Q10 estimation (smaller median relative bias, RMSE, RRMSE, and UA-RMSE, especially for basins larger than 100 mi2). The success of calibration is extended to ungaged locations using the machine learning algorithm Fuzzy C-Means (FCM) clustering, finding that traditional K-Means clustering (FCM clustering with no fuzzification factor) is the preferred method for model regionalization based on (1) Silhouette Analysis, (2) daily streamflow KGE, and (3) 7Q10 error metrics. The optimal rainfall-runoff models created with clustering show improvement for daily streamflow estimation (a median KGE of 0.48, only slightly below that of the calibrated models at 0.52); however, these models display similar error metrics for 7Q10 estimation compared to the uncalibrated models, neither of which provide improved error compared to the statistical estimates. Results suggest that the rainfall-runoff models calibrated to measured streamflow data provide the best 7Q10 estimation in terms of all error metrics except median relative bias, but for all models applicable to ungaged locations, the statistical estimates from StreamStats display the lowest error metrics in every category.

Short-term wind power forecasting based on dual attention mechanism and gated recurrent unit neural network

Accurate wind power forecasting is essential for both optimal grid scheduling and the massive absorption of wind power into the grid. However, the continuous changes in the contribution of various meteorological features to the forecasting of wind power output under different time or weather conditions, and the overlapping of wind power sequence cycles, make forecasting challenging. To address these problems, a short-term wind power forecasting model is established that integrates a gated recurrent unit (GRU) network with a dual attention mechanism (DAM). To compute the contributions of different features in real time, historical wind power data and meteorological information are first extracted using a feature attention mechanism (FAM). The feature sequences collected by the FAM are then used by the GRU network for preliminary forecasting. Subsequently, one-dimensional convolution employing several distinct convolution kernels is used to filter the GRU outputs. In addition, a multi-head time attention mechanism (MHTAM) is proposed and a Gaussian bias is introduced to assign different weights to different time steps of each modality. The final forecast results are produced by combining the outputs of the MHTAM. The results of the simulation experiment show that for 5-h, 10-h, and 20-h short-term wind power forecasting, the established DAM-GRU model performs better than comparative models on the basis of Root Mean Square Error (RMSE), Mean Absolute Error (MAE), R-squared (R2), Square sum error (SSE), Mean absolute percentile error (MAPE), and Relative root mean square error (RRMSE) index.

Fast prediction of patient-specific organ doses in brain CT scans using support vector regression algorithm.

Objectives. This study aims to develop a method for predicting patient-specific head organ doses by training a support vector regression (SVR) model based on radiomics features and graphics processing unit (GPU)-calculated reference doses.Methods. In this study, 237 patients who underwent brain CT scans were selected, and their CT data were transferred to an autosegmentation software to segment head regions of interest (ROIs). Subsequently, radiomics features were extracted from the CT data and ROIs, and the benchmark organ doses were computed using fast GPU-accelerated Monte Carlo (MC) simulations. The SVR organ dose prediction model was then trained using the radiomics features and benchmark doses. For the predicted organ doses, the relative root mean squared error (RRMSE), mean absolute percentage error (MAPE), and coefficient of determination (R2) were evaluated. The robustness of organ dose prediction was verified by changing the patient samples on the training and test sets randomly.Results. For all head organs, the maximal difference between the reference and predicted dose was less than 1 mGy. For the brain, the organ dose was predicted with an absolute error of 1.3%, and theR2reached up to 0.88. For the eyes and lens, the organ doses predicted by SVR achieved an RRMSE of less than 13%, the MAPE ranged from 4.5% to 5.5%, and theR2values were more than 0.7.Conclusions. Patient-specific head organ doses from CT examinations can be predicted within one second with high accuracy, speed, and robustness by training an SVR using radiomics features.

A Novel Approach for Simultaneous Localization and Dense Mapping Based on Binocular Vision in Forest Ecological Environment

The three-dimensional reconstruction of forest ecological environment by low-altitude remote sensing photography from Unmanned Aerial Vehicles (UAVs) provides a powerful basis for the fine surveying of forest resources and forest management. A stereo vision system, D-SLAM, is proposed to realize simultaneous localization and dense mapping for UAVs in complex forest ecological environments. The system takes binocular images as input and 3D dense maps as target outputs, while the 3D sparse maps and the camera poses can be obtained. The tracking thread utilizes temporal clue to match sparse map points for zero-drift localization. The relative motion amount and data association between frames are used as constraints for new keyframes selection, and the binocular image spatial clue compensation strategy is proposed to increase the robustness of the algorithm tracking. The dense mapping thread uses Linear Attention Network (LANet) to predict reliable disparity maps in ill-posed regions, which are transformed to depth maps for constructing dense point cloud maps. Evaluations of three datasets, EuRoC, KITTI and Forest, show that the proposed system can run at 30 ordinary frames and 3 keyframes per second with Forest, with a high localization accuracy of several centimeters for Root Mean Squared Absolute Trajectory Error (RMS ATE) on EuRoC and a Relative Root Mean Squared Error (RMSE) with two average values of 0.64 and 0.2 for trel and Rrel with KITTI, outperforming most mainstream models in terms of tracking accuracy and robustness. Moreover, the advantage of dense mapping compensates for the shortcomings of sparse mapping in most Smultaneous Localization and Mapping (SLAM) systems and the proposed system meets the requirements of real-time localization and dense mapping in the complex ecological environment of forests.

A coarse pixel-scale ground “truth” dataset based on global in situ site measurements to support validation and bias correction of satellite surface albedo products

Abstract. In situ measurements from sparsely distributed networks worldwide are a critical source of reference data for validating or correcting biases in satellite products. However, due to the substantial difference in spatial scales between in situ and satellite measurements, the two cannot be compared except for the fact that the underlying surface of in situ sites is absolutely homogeneous. Instead, the in situ measurements needed to be upscaled to be matched with the satellite pixels. Based on the upscaling model, we also proposed the consideration that in situ observation generally lacks spatial representativeness due to the widely distributed spatial heterogeneity, and we have developed a coarse pixel-scale ground “truth” dataset based on ground measurements of 416 in situ sites from the sparsely distributed observation networks. Furthermore, we thoroughly assessed the effectiveness of the dataset at sites with different degrees of spatial representativeness. The results demonstrate that using this dataset in validation outperforms the direct comparison between satellite and in situ site measurements over heterogeneous surfaces when in situ measurement footprints are less than satellite pixel size. The accuracy of the reference data employed for validation or bias correction can be boosted by 17.09 % over the regions with strong spatial heterogeneity. However, the degree of improvement with this dataset displays a decreasing trend with the reduction in spatial heterogeneity. At a global scale, the pixel-scale ground “truth” dataset enhances the accuracy of pixel-scale reference data in general, with the overall relative root-mean-square error (RRMSE) decreasing by 6.04 % compared to in situ single-site measurements. Our results suggest that in situ single-site measurements are limited in their ability to capture surface spatial variability information at a coarse pixel scale (i.e., the kilometer scale). The dataset we provided, which merges temporal information from ground-based observations and spatial information from high-resolution data, represents a valuable resource for validating and correcting worldwide surface albedo products over heterogeneous surfaces. To the best of our knowledge, this dataset is unique in providing a coarse pixel-scale ground “truth” with the widest spatial distribution and longest time series. The dataset is publicly available through https://doi.org/10.5281/zenodo.8008454 (Pan et al., 2023).

Estimating reference crop evapotranspiration using improved convolutional bidirectional long short-term memory network by multi-head attention mechanism in the four climatic zones of China

Accurate reference crop evapotranspiration (ET0) estimation is essential for agricultural water management, crop productivity, and irrigation systems. As the standard ET0 estimation method, the Penman-Monteith equation has been widely recommended worldwide. However, its application is still restricted to comprehensive meteorological data deficiency, making the exploration of alternative simpler models for acceptable ET0 estimation highly meaningful. Concerning the aforementioned requirement, this study developed the novel deep learning model (MA-CNN-BiLSTM), which incorporates Multi-Head Attention mechanism (MA), Convolutional Neural Network (CNN), and Bidirectional Long Short-Term Memory network (BiLSTM) as intricate relationship processor, feature extractor, and regression component, to estimate ET0 based on radiation-based (Rn-based), humidity-based (RH-based), and temperature-based (T-based) input combinations at 600 stations during 1961–2020 throughout China under internal and external cross-validation strategies. Besides, through a comparative evaluation among MA-CNN-BiLSTM, CNN-BiLSTM, BiLSTM, LSTM, Multivariate Adaptive Regression Splines (MARS), and empirical models, the result indicated that MA-CNN-BiLSTM achieved superior precision, with values of Determination Coefficient (R2), Nash–Sutcliffe efficiency coefficient (NSE), Relative Root Mean Square Error (RRMSE), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE) ranging 0.877–0.972, 0.844–0.962, 0.129–0.292, 0.294–0.644 mm d−1, 0.244–0.566 mm d−1 for internal strategy and 0.797–0.927, 0.786–0.920, 0.162–0.335, 0.409–0.969 mm d−1, 0.294–0.699 mm d−1 for external strategy. Specifically, Rn-based MA-CNN-BiLSTM excelled in the temperate continental zone (TCZ) and mountain plateau zone (MPZ), while RH-based MA-CNN-BiLSTM yielded best precision in others. Furthermore, the internal strategy was superior to external strategy by 2.74–106.04% for R2, 1.11–120.49% for NSE, 1.41–40.27% for RRMSE, 1.68–45.53% for RMSE, and 1.21–38.87% for MAE, respectively. In summary, the main contribution of the present study is the proposal of a novel LSTM-type ET0 model (MA-CNN-BiLSTM) to cope with various data-missing scenarios throughout China, which can provide effective support for decision-making in regional agriculture water management.

Modeling sugarcane development and growth within ECOSMOS biophysical model

Sugarcane plays an important role in electricity and sugar production and is a viable biofuel. Developing and optimizing a mechanism that can predict crop growth and yield at different spatiotemporal scales can promote the understanding of the effects of cultivation on the ecosystem, while providing options for optimizing management measures and improving the operational procedures of sugarcane growers. The main objective of this study is to integrate the sugarcane module into the ECOSystem MOdel Simulator (ECOSMOS) model and calibrate a parameter set for sugarcane genotypes groups (using different datasets); the model supports datasets that vary in complexity (from flux tower experiments to operational plots), while accounting for high genotype-by-environment-by-management (GxExM) variability. First, we calibrated the ECOSMOS biophysical and physiological parameters for the sugarcane module using two micrometeorological experimental sites, based on eddy-covariance and biomass measurements. Second, sugarcane genotypes located in different regions of contrasting climate conditions were split into two groups based on their period of harvest, i.e., early or mid-to-late harvest season, and two parameter sets were proposed. The sugarcane module was used to estimate the yield of numerous plots, using two different parameter sets, namely, the general and regionally-specific parameter sets. The model could successfully simulate the biophysical and physiological processes of the biomass of stalks and leaves, energy and carbon fluxes, and soil-water dynamics; for Experimental Site 2, the Nash-Sutcliffe efficiency (NSE) was 0.14–0.86 and the relative root mean square error (RRMSE) was 13–112. However, the generic parameter set did not perform well in all production environments, and the difference between the observed and simulated yields ranged from 0.9 to 14.5 (Mg ha-1). Hence, a novel calibration approach adopted in this study improved the module’s accuracy, while improving the performances for all five production environments, with the difference between the observed and simulate yields being 0.3–2.2 (Mg ha-1). Although the two parameter sets can be used as a reference for sugarcane plantations in Brazil, we recommend recalibrating the model (for ensuring higher accuracy) before operational applications. Notably, the ECOSMOS-sugarcane model is emerging as a complex ecosystem model that can support the quantifications and evaluations of the effects of sugarcane plantations on the carbon and water balances in different environmental conditions, particularly in tropical regions.

Application of Artificial Intelligence Technology in Electromechanical Information Security Situation Awareness System

The information security situational awareness system is proposed in this paper to leverage big data and artificial intelligence (AI) to enhance information security situation prediction. Deep learning techniques, specifically the long short-term memory recurrent neural network (LSTM-RNN), predict security situations using complex non-linear and autocorrelation time series data from current and past system conditions. Additionally, the study incorporates the variant gated recurrent unit (GRU) within the LSTM-RNN framework. A comprehensive experimental analysis is conducted, comparing various methods, including LSTM, GRU, and others, to assess and compare their predictive performance. The experimental results reveal that LSTM-RNN demonstrates a commendable level of predictive accuracy on the test dataset, with a mean absolute percentage error (MAPE) of 8.79%, a root mean square error (RMSE) of 0.1107, and a relative root mean square error (RRMSE) of 8.47%. Both LSTM and GRU exhibit exceptional predictive accuracy, with GRU offering a slightly faster training speed due to its simplified architecture and fewer trainable parameters. Overall, this research highlights the potential of AI-based methodologies in constructing robust information security situational awareness systems.

Retrieval of snow water equivalent from dual-frequency radar measurements: using time series to overcome the need for accurate a priori information

Abstract. Measurements of radar backscatter are sensitive to snow water equivalent (SWE) across a wide range of frequencies, motivating proposals for satellite missions to measure global distributions of SWE. However, radar backscatter measurements are also sensitive to snow stratigraphy, to microstructure, and to ground surface roughness, complicating SWE retrieval. A number of recent advances have created new tools and datasets with which to address the retrieval problem, including a parameterized relationship between SWE, microstructure, and radar backscatter, and methods to characterize ground surface scattering. Although many algorithms also introduce external (prior) information on SWE or snow microstructure, the precision of the prior datasets used must be high in some cases in order to achieve accurate SWE retrieval. We hypothesize that a time series of radar measurements can be used to solve this problem and demonstrate that SWE retrieval with acceptable error characteristics is achievable by using previous retrievals as priors for subsequent retrievals. We demonstrate the accuracy of three configurations of prior information: using a global SWE model, using the previously retrieved SWE, and using a weighted average of the model and the previous retrieval. We assess the robustness of the approach by quantifying the sensitivity of the SWE retrieval accuracy to SWE biases artificially introduced in the prior. We find that the retrieval with the weighted averaged prior demonstrates SWE accuracy better than 20 % and an error increase of only 3 % relative RMSE per 10 % change in prior bias; the algorithm is thus both accurate and robust. This finding strengthens the case for future radar-based satellite missions to map SWE globally.