Reduction In RMSE Research Articles

KF-Loc: A Kalman Filter and Machine Learning Integrated Localization System Using Consumer-Grade Millimeter-Wave Hardware

With the ever-increasing demands of e-commerce, the need for smarter warehousing is increasing exponentially. Such warehouses require industry automation beyond Industry 4.0. In this work, we use consumer-grade millimeter-wave (mmWave) equipment to enable fast, and low-cost implementation of our localization system. However, the consumer-grade mmWave routers suffer from coarse-grained channel state information due to cost-effective antenna array design limiting the accuracy of localization systems. To address these challenges, we present a machine learning (ML) and Kalman filter (KF) integrated localization system (KF-Loc). The ML model learns the complex wireless features for predicting the static position of the robot. When in dynamic motion, the static ML estimates suffer from position mispredictions, resulting in loss of accuracy. To overcome the loss in accuracy, we design and integrate a KF that learns the dynamics of the robot motion to provide highly accurate tracking. Our system achieves centimeter-level accuracy for the two aisles with RMSE of 0.35 m and 0.37 m, respectively. Further, compared with ML only localization systems, we achieve a significant reduction in RMSE by 28.5% and 54.3% within the two aisles.

Improving Wheat Yield Prediction Accuracy Using LSTM-RF Framework Based on UAV Thermal Infrared and Multispectral Imagery

Yield prediction is of great significance in agricultural production. Remote sensing technology based on unmanned aerial vehicles (UAVs) offers the capacity of non-intrusive crop yield prediction with low cost and high throughput. In this study, a winter wheat field experiment with three levels of irrigation (T1 = 240 mm, T2 = 190 mm, T3 = 145 mm) was conducted in Henan province. Multispectral vegetation indices (VIs) and canopy water stress indices (CWSI) were obtained using an UAV equipped with multispectral and thermal infrared cameras. A framework combining a long short-term memory neural network and random forest (LSTM-RF) was proposed for predicting wheat yield using VIs and CWSI from multi-growth stages as predictors. Validation results showed that the R2 of 0.61 and the RMSE value of 878.98 kg/ha was achieved in predicting grain yield using LSTM. LSTM-RF model obtained better prediction results compared to the LSTM with n R2 of 0.78 and RMSE of 684.1 kg/ha, which is equivalent to a 22% reduction in RMSE. The results showed that LSTM-RF considered both the time-series characteristics of the winter wheat growth process and the non-linear characteristics between remote sensing data and crop yield data, providing an alternative for accurate yield prediction in modern agricultural management.

Assessment of RTK Quadcopter and Structure-from-Motion Photogrammetry for Fine-Scale Monitoring of Coastal Topographic Complexity

Advances in image-based remote sensing using unmanned aerial vehicles (UAV) and structure-from-motion (SfM) photogrammetry continue to improve our ability to monitor complex landforms over representative spatial and temporal scales. As with other water-worked environments, coastal sediments respond to shaping processes through the formation of multi-scale topographic roughness. Although this topographic complexity can be an important marker of hydrodynamic forces and sediment transport, it is seldom characterized in typical beach surveys due to environmental and technical constraints. In this study, we explore the feasibility of using SfM photogrammetry augmented with an RTK quadcopter for monitoring the coastal topographic complexity at the beach-scale in a macrotidal environment. The method had to respond to resolution and time constraints for a realistic representation of the topo-morphological features from submeter dimensions and survey completion in two hours around low tide to fully cover the intertidal zone. Different tests were performed at two coastal field sites with varied dimensions and morphologies to assess the photogrammetric performance and eventual means for optimization. Our results show that, with precise image positioning, the addition of a single ground control point (GCP) enabled a global precision (RMSE) equivalent to that of traditional GCP-based photogrammetry using numerous and well-distributed GCPs. The optimal model quality that minimized vertical bias and random errors was achieved from 5 GCPs, with a two-fold reduction in RMSE. The image resolution for tie point detection was found to be an important control on the measurement quality, with the best results obtained using images at their original scale. Using these findings enabled designing an efficient and effective workflow for monitoring coastal topographic complexity at a large scale.

Using an Adaptive Neuro-Fuzzy Inference System to Predict Dilution Characteristics of Vertical Buoyant Jets Subjected to Lateral Confinement

In order to predict the dilution characteristics of vertical buoyant jets constrained by lateral obstructions, we propose a new method based on a commonly used machine learning algorithm: the adaptive neuro-fuzzy inference system (ANFIS). By using experimental data to train and test the ANFIS model, this study shows that it had better performance than commonly used empirical equations for laterally confined jets and another artificial intelligence technique—genetic programming. The RMSE values of the ANFIS-based model were lower, and the R2 values were higher, compared with those of the empirical equation and genetic programming models. The reduction in RMSE achieved by using ANFIS to replace the empirical equations or genetic programming algorithm exceeded 20%. This research confirms that the ANFIS technique has real potential in the development of effective and accurate models that can be used to estimate the dilution characteristics of a vertical buoyant jet subjected to lateral confinement, providing a new avenue for the prediction of dilution characteristics using artificial intelligence techniques, which can also be utilized for other effluent mixing problems in marine systems.

Frequency Diversity in Electromagnetic Remote Sensing of Lower Atmospheric Refractivity

This article explores the effects of system frequency on electromagnetic (EM) remote sensing of atmospheric refractivity. A frequency range of 2–40 GHz covering S- to Ka-bands is analyzed. A multifrequency inversion algorithm is developed to estimate the evaporation duct heights using a parabolic wave equation propagation model. The capabilities of a theoretical multifrequency system are explored for high and low signal-to-noise ratios for varying numbers of frequencies and bands. Experimental data were collected using the lower atmospheric propagation ultrawideband (LATPROP-UWB) system deployed during the Coupled Air-Sea Processes and EM Ducting Research (CASPER) East Campaign. Range-dependent propagation loss measurements at 53 frequencies ranging from 2 to 40 GHz were made. The evaporation duct refractivity profiles estimated from the multifrequency LATPROP-UWB data were compared to the profiles inferred from the concurrent meteorological and oceanographic measurements. Inversion results show that the optimal refractivity retrieval can be achieved using ten frequencies and results in a fourfold reduction in the estimation RMSE compared to a single-frequency inversion.

Multi‐Sensor Approach for High Space and Time Resolution Land Surface Temperature

AbstractSurface‐atmosphere fluxes and their drivers vary across space and time. A growing area of interest is in downscaling, localizing, and/or resolving sub‐grid scale energy, water, and carbon fluxes and drivers. Existing downscaling methods require inputs of land surface properties at relatively high spatial (e.g., sub‐kilometer) and temporal (e.g., hourly) resolutions, but many observed land surface drivers are not continuously available at these resolutions. We evaluate an approach to overcome this challenge for land surface temperature (LST), a World Meteorological Organization Essential Climate Variable and a key driver for surface heat fluxes. The Chequamegon Heterogenous Ecosystem Energy‐balance Study Enabled by a High‐density Extensive Array of Detectors (CHEESEHEAD19) field experiment provided a scalable testbed. We downscaled LST from satellites (GOES‐16 and ECOsystem Spaceborne Thermal Radiometer Experiment on Space Station [ECOSTRESS]) with further refinement using airborne hyperspectral imagery. Temporally and spatially downscaled LST compared well to independent observations from a network of 20 micrometeorological towers and piloted aircrafts in addition to Landsat‐based LST retrieval and drone‐based LST observed at one tower site. The downscaled 50‐m hourly LST showed good relationships with tower (r2 = 0.79, RMSE = 3.5 K) and airborne (r2 = 0.75, RMSE = 2.4 K) observations over space and time, with precision lower over wetlands and lakes, and some improvement for capturing spatio‐temporal variation compared to a geostationary satellite. Further downscaling to 10 m using hyperspectral imagery resolved hot and cold spots across the landscape as evidenced by independent drone LST, with significant reduction in RMSE by 1.3 K. These results demonstrate a simple pathway for multi‐sensor retrieval of high space and time resolution LST.

Implementation of stacking based ARIMA model for prediction of Covid-19 cases in India

BackgroundTime-series forecasting has a critical role during pandemics as it provides essential information that can lead to abstaining from the spread of the disease. The novel coronavirus disease, COVID-19, is spreading rapidly all over the world. The countries with dense populations, in particular, such as India, await imminent risk in tackling the epidemic. Different forecasting models are being used to predict future cases of COVID-19. The predicament for most of them is that they are not able to capture both the linear and nonlinear features of the data solely. MethodsWe propose an ensemble model integrating an autoregressive integrated moving average model (ARIMA) and a nonlinear autoregressive neural network (NAR). ARIMA models are used to extract the linear correlations and the NAR neural network for modeling the residuals of ARIMA containing nonlinear components of the data.Comparison: Single ARIMA model, ARIMA-NAR model and few other existing models which have been applied on the COVID-19 data in different countries are compared based on performance evaluation parameters. ResultThe hybrid combination displayed significant reduction in RMSE (16.23%), MAE (37.89%) and MAPE (39.53%) values when compared with single ARIMA model for daily observed cases. Similar results with reduced error percentages were found for daily reported deaths and cases of recovery as well. RMSE value of our hybrid model was lesser in comparison to other models used for forecasting COVID-19 in different countries. ConclusionResults suggested the effectiveness of the new hybrid model over a single ARIMA model in capturing the linear as well as nonlinear patterns of the COVID-19 data.

Assessing new intra-daily temperature-based machine learning models to outperform solar radiation predictions in different conditions

The measure of solar radiation is costly, as well as its maintenance and calibration needs; therefore, reliable datasets are scarce. In this work, several machine learning models to predict solar radiation have been developed and assessed at nine locations (Southern Spain and North Carolina in the USA), representing different geo-climatic conditions (aridity, sea distance, and elevation). As a novelty, due to the ease of providing air temperature measurements, different new input variables from intra-daily temperature datasets were used. According to the results, all the models highly outperformed self-calibrated empirical methods such as Hargreaves-Samani and Bristow-Campbell, with improvements in RMSE ranging from 7.56% in arid climate to 45.65% in humid. Moreover, regarding mean NSE and R2 values, several inland locations obtained values above 0.9. In summer, the highest statistics for all sites (more than a 60% improvement in NSE and R2) were obtained, whereas the worst were given in winter (more than an 18% improvement in NSE and R2). Besides, when assessing the models in different non-used locations with similar climatic characteristics, the reduction in RMSE was from 0.305 W m−2 to 0.252 W m−2 in a semiarid coastal climate and from 0.344 W m−2 to 0.233 W m−2 in dry sub-humid climate, compared to Hargreaves-Samani method. Overall, the MLP obtained the highest performance using the new proposed variables in all locations with medium aridity values, whereas in the aridest and most humid sites, SVM and RF models were preferred. Therefore, the temperature-based models developed in this work can predict solar radiation more accurately than the current ones. This is crucial in locations with no available datasets or missing/low quality and can be used to optimize the determination of the potential locations for solar power plants' construction.

Improvement of multi‐layer soil moisture prediction using support vector machines and ensemble Kalman filter coupled with remote sensing soil moisture datasets over an agriculture dominant basin in China

AbstractSoil moisture prediction is of great importance in crop yield forecasting and drought monitoring. In this study, the multi‐layer root zone soil moisture (0‐5, 0‐10, 10‐40 and 40‐100 cm) prediction is conducted over an agriculture dominant basin, namely the Xiang River Basin, in southern China. The support vector machines (SVM) coupled with dual ensemble Kalman filter (EnKF) technique (SVM‐EnKF) is compared with SVM for its potential capability to improve the efficiency of soil moisture prediction. Three remote sensing soil moisture products, namely SMAP, ASCAT and AMSR2, are evaluated for their performance in multi‐layer soil moisture prediction with SVM and SVM‐EnKF, respectively. Multiple cases are designed to investigate the performance of SVM, the effectiveness of coupling dual EnKF technique and the applicability of the remote sensing products in soil moisture prediction. The main results are as follows: (a) The efficiency of soil moisture prediction with SVM using meteorological variables as inputs is satisfactory for the surface layers (0‐5 and 0‐10 cm), while poor for the root zone layers (10‐40 and 40‐100 cm). Adding SMAP as input to SVM can improve its performance in soil moisture prediction, with more than 47% increase in theR‐value and at least 11% reduction in RMSE for all layers. However, adding ASCAT or AMSR2 has no improvement for its performance. (b) Coupling dual EnKF can significantly improve the performance of SVM in the soil moisture prediction of both surface and the root zone layers. The increase inR‐value is above 80%, while the reduction in BIAS and RMSE is respectively more than 90% and 63%. However, adding remote sensing soil moisture products as inputs can no further improve the performance of SVM‐EnKF. (c) The SVM‐EnKF can eliminate the influence of remote sensing soil moisture extreme values in soil moisture prediction, therefore, improve its accuracy.

Developing Pseudo Continuous Pedotransfer Functions for International Soils Measured with the Evaporation Method and the HYPROP System: II. The Soil Hydraulic Conductivity Curve

Direct measurement of unsaturated hydraulic parameters is costly and time-consuming. Pedotransfer functions (PTFs) are typically developed to estimate soil hydraulic properties from readily available soil attributes. For the first time, in this study, we developed PTFs to estimate the soil hydraulic conductivity (log(K)) directly from measured data. We adopted the pseudo continuous neural network PTF (PCNN-PTF) approach and assessed its accuracy and reliability using two independent data sets with hydraulic conductivity measured via the evaporation method. The primary data set contained 150 international soils (6963 measured data pairs), and the second dataset consisted of 79 repacked Turkish soil samples (1340 measured data pairs). Four models with different combinations of the input attributes, including soil texture (sand, silt, clay), bulk density (BD), and organic matter content (SOM), were developed. The best performing international (root mean square error, RMSE = 0.520) and local (RMSE = 0.317) PTFs only had soil texture information as inputs when developed and tested using the same data set to estimate log(K). However, adding BD and SOM as input parameters increased the reliability of the international PCNN-PTFs when the Turkish data set was used as the test data set. We observed an overall improvement in the performance of PTFs with the increasing number of data points per soil textural class. The PCNN-PTFs consistently performed high across tension ranges when developed and tested using the international data set. Incorporating the Turkish data set into PTF development substantially improved the accuracy of the PTFs (on average close to 60% reduction in RMSE). Consequently, we recommend integrating local HYPROPTM (Hydraulic Property Analyzer, Meter Group Inc., USA) data sets into the international data set used in this study and retraining the PCNN-PTFs to enhance their performance for that specific region.

Structural-Information-Based Robust Corner Point Extraction for Camera Calibration Under Lens Distortions and Compression Artifacts

Previous camera calibration methods often use a checkerboard to capture images and estimate the camera parameters from the correspondences between images and the checkerboard. The corner points in the checkerboard images are used as useful features for correspondence matching. Therefore, it is essential to precisely find the corner points in the checkerboard images. In many previous works, the corner points are extracted assuming that the checkerboard images are not distorted by its lens. Instead, image blurring and Gaussian noise on the images are usually considered, but other cases are not dealt with. However, the captured checkerboard images are often corrupted by lens distortions and compression artifacts, which leads to performance degradation of corner point extraction. Moreover, the corner points are extracted individually in the previous methods without considering their geometric relations. To better handle the corner point extraction problem under lens distortions, in our corner point extraction optimization, the distorted locations of the pixels on checkerboard images are corrected with the camera parameters, and the structural constraints for checkerboard image grids are then applied under the line-to-line mapping. Also, to robustly find the blurred edges between corner points due to JPEG compression, an edge surface model is newly proposed that models the transitions with over- and under-shoots around the blurred edges. Extensive experimental results show that our method significantly outperforms the state-of-the-art method with average 88.3% and 54.3% reduction in RMSE for corner point reprojection and camera parameter estimation, respectively under compression and lens distortions for synthetic and real data.

A non-parametric Hawkes model of the spread of Ebola in west Africa

ABSTRACT Recently developed methods for the non-parametric estimation of Hawkes point process models facilitate their application for describing and forecasting the spread of epidemic diseases. We use data from the 2014 Ebola outbreak in West Africa to evaluate how well a simple Hawkes point process model can forecast the spread of Ebola virus in Guinea, Sierra Leone, and Liberia. For comparison, SEIR models that fit previously to the same data are evaluated using identical metrics. To test the predictive power of each of the models, we simulate the ability to make near real-time predictions during an actual outbreak by using the first 75% of the data for estimation and the subsequent 25% of the data for evaluation. Forecasts generated from Hawkes models more accurately describe the spread of Ebola in each of the three countries investigated and result in a 38% reduction in RMSE for weekly case estimation across all countries when compared to SEIR models (total RMSE of 59.8 cases/week using SEIR compared to 37.1 for Hawkes). We demonstrate that the improved fit from Hawkes modeling cannot be attributed to overfitting and evaluate the advantages and disadvantages of Hawkes models in general for forecasting the spread of epidemic diseases.

Evaluation of CORDEX- South Asia regional climate models for heat wave simulations over India

The episodes of heat wave events have strengthened in recent decades causing great concern for human health, agriculture and natural ecosystem. In the present study, Regional Climate Models (RCMs) namely, CCAM and RegCM, from Coordinated Regional Climate Downscaling Experiments (CORDEX) for South Asia (SA) are evaluated for simulating heat waves (March–June) for a long-term period (1971 to 2005) over India in comparison with observations from India Meteorological Department (IMD). The statistical analysis (correlation, RMSE, MAE, ECDF) results reveal differences in RCMs in simulating spatial pattern and trends of maximum temperature before bias correction. Variance scaling bias correction is found to remove bias and improve model simulations in capturing temperature variability. An increase in correlation in daily observations from 0.24 to 0.70 and reduction in RMSE from 8.08 °C to 2.02 °C and MAE from 3.87 °C to 2.43 °C after bias correction is observed between model and observation.LMDZ4 and GFDL-ESM2M are found to perform best in simulating interannual variability of seasonal mean maximum temperature with an underestimation of −7.74% and −15.41% which improved significantly to around −1.51% and − 0.78%, respectively after bias correction over India. LMDZ4 and GFDL-ESM2M are also best-performing models in significantly reproducing the heat wave frequency and spatial variability in closer proximity with observations over India amongst all models after bias correction. Over NW and western regions, the LMDZ4 and GFDL-ESM2M ensemble models successfully capture the increasing trend of 0.2 events/year and 0.4 events/year accordance to IMD and IITM criteria, respectively. However, the ACCESS1.0, CNRM-CM5 and CCSM4 ensemble experiments overestimated heat waves by ±40 events in most sub-divisions in India. Over the central Indian regions, the ACCESS 1.0 and CNRM-CM5 model output show a negative trend of −0.2 events/year and large spatial variability possibly due to model associated uncertainties. Overall the results show an improvement in capturing maximum temperature and heat waves across the regions of Indian sub-continent in the bias-corrected downscaled CORDEX-SA ensemble RCMs than without bias-corrected output. The study suggests a way forward to assess RCMs performance and uncertainty in extreme weather analysis in future projections.

Modeling yield response to crop management using convolutional neural networks

Predicting crop yield response to management and environmental variables is a crucial step towards nutrient management optimization. With the increase in the amount of data generated by agricultural machinery, more sophisticated models are necessary to get full advantage of such data. In this work, we propose a Convolutional Neural Network (CNN) to capture relevant spatial structures of different attributes and combine them to model yield response to nutrient and seed rate management. Nine on-farm experiments on corn fields are used to construct a suitable dataset to train and test the CNN model. Four architectures combining input attributes at different stages in the network are evaluated and compared to the most commonly used predictive models. Results show a reduction in the test dataset RMSE up to 68% when compared to multiple linear regression and up to 29% when compared to a random forest. We also demonstrate that higher variability associated with the spatial structure of the data takes the most advantage of this framework.

Symbolic regression-based improved method for wind speed extrapolation from lower to higher altitudes for wind energy applications

Prolonged wind speed assessment at higher altitudes is essential for wind energy estimation and planning. However, the erection and maintenance of tall wind measuring masts for this purpose cause many practical inconveniences from the engineering perspective. A rather simplified method often used for this task is to measure the wind profile at relatively lower altitudes and extrapolate the same to the required higher heights by empirical equations framed using hypothetical and experiential research. Such models often show errors due to the uncertainties caused by the complex nature of turbulent flows and the terrain. In this paper, we propose a new method of applying symbolic regression to the wind speed data over a short duration measured at a reference location to obtain a symbolic function capable of estimating wind speeds at higher altitudes using wind speed data at lower altitudes at different locations. Compared to the traditional power law method, the new method performs more accurately in different seasons at the reference as well as far away locations, achieving a maximum of 61.04% reduction in daily RMSE when analyzed with wind speeds averaged over 10-min intervals in this study. The new method opens up the possibility of wind resource assessment at higher altitudes at different locations by employing engineering-friendly shorter wind measuring masts.

Genetic Algorithm Based Optimum Solar Power Prediction by Environmental Features for Indian Railway Stations

Electric Power requirement is increasing with every new day. Bulk of electric power in India is consumed by Indian railways, hence green energy resources are required to reduce this load. Out of many available green energy resources solar energy is playing an important role. Hence desired optimum power output from solar plant is always of area of research. This work focuses on estimation of solar plant output with the affecting environmental variables by using genetic algorithm. Genetic algorithm predicts the ratio of environmental variables that directly increase or decrease the solar power output. Work will determine this ratio by using modified butterfly particle swarm optimization algorithm and Teacher Learning Based Optimization. Here it was obtained that proposed TLBO model is good for estimating monthly power prediction while MBAPSO estimate accurate values for daily power prediction. Proposed model experiment was done on dataset of Raipur city in Chhattisgarh state of India and the results show reduction in MAE, RMSE and improvement in Correlation Coefficient thereby accuracy in power prediction when compared with ground truth values taken from Indian railway top roof solar installation.

Mitigating inherent noise in Monte Carlo dose distributions using dilated U-Net.

Monte Carlo (MC) algorithms offer accurate modeling of dose calculation by simulating the transport and interactions of many particles through the patient geometry. However, given their random nature, the resulting dose distributions have statistical uncertainty (noise), which prevents making reliable clinical decisions. This issue is partly addressable using a huge number of simulated particles but is computationally expensive as it results in significantly greater computation times. Therefore, there is a trade-off between the computation time and the noise level in MC dose maps. In this work, we address the mitigation of noise inherent to MC dose distributions using dilated U-Net - an encoder-decoder-styled fully convolutional neural network, which allows fast and fully automated denoising of whole-volume dose maps. We use mean squared error (MSE) as loss function to train the model, where training is done in 2D and 2.5D settings by considering a number of adjacent slices. Our model is trained on proton therapy MC dose distributions of different tumor sites (brain, head and neck, liver, lungs, and prostate) acquired from 35 patients. We provide the network with input MC dose distributions simulated using particles while keeping particles as reference. After training, our model successfully denoises new MC dose maps. On average (averaged over five patients with different tumor sites), our model recovers of 55.99Gy from the noisy MC input of 49.51Gy, whereas the low noise MC (reference) offers 56.03Gy. We observed a significant reduction in average RMSE (thresholded >10% max ref) for reference vs denoised (1.25Gy) than reference vs input (16.96Gy) leading to an improvement in signal-to-noise ratio (ISNR) by 18.06dB. Moreover, the inference time of our model for a dose distribution is less than 10s vs 100min (MC simulation using particles). We propose an end-to-end fully convolutional network that can denoise Monte Carlo dose distributions. The networks provide comparable qualitative and quantitative results as the MC dose distribution simulated with particles, offering a significant reduction in computation time.

Exploring the Utility of Machine Learning-Based Passive Microwave Brightness Temperature Data Assimilation over Terrestrial Snow in High Mountain Asia

This study explores the use of a support vector machine (SVM) as the observation operator within a passive microwave brightness temperature data assimilation framework (herein SVM-DA) to enhance the characterization of snow water equivalent (SWE) over High Mountain Asia (HMA). A series of synthetic twin experiments were conducted with the NASA Land Information System (LIS) at a number of locations across HMA. Overall, the SVM-DA framework is effective at improving SWE estimates (~70% reduction in RMSE relative to the Open Loop) for SWE depths less than 200 mm during dry snowpack conditions. The SVM-DA framework also improves SWE estimates in deep, wet snow (~45% reduction in RMSE) when snow liquid water is well estimated by the land surface model, but can lead to model degradation when snow liquid water estimates diverge from values used during SVM training. In particular, two key challenges of using the SVM-DA framework were observed over deep, wet snowpacks. First, variations in snow liquid water content dominate the brightness temperature spectral difference (ΔTB) signal associated with emission from a wet snowpack, which can lead to abrupt changes in SWE during the analysis update. Second, the ensemble of SVM-based predictions can collapse (i.e., yield a near-zero standard deviation across the ensemble) when prior estimates of snow are outside the range of snow inputs used during the SVM training procedure. Such a scenario can lead to the presence of spurious error correlations between SWE and ΔTB, and as a consequence, can result in degraded SWE estimates from the analysis update. These degraded analysis updates can be largely mitigated by applying rule-based approaches. For example, restricting the SWE update when the standard deviation of the predicted ΔTB is greater than 0.05 K helps prevent the occurrence of filter divergence. Similarly, adding a thin layer (i.e., 5 mm) of SWE when the synthetic ΔTB is larger than 5 K can improve SVM-DA performance in the presence of a precipitation dry bias. The study demonstrates that a carefully constructed SVM-DA framework cognizant of the inherent limitations of passive microwave-based SWE estimation holds promise for snow mass data assimilation.

Hyperspectral Leaf Reflectance as Proxy for Photosynthetic Capacities: An Ensemble Approach Based on Multiple Machine Learning Algorithms.

Global agriculture production is challenged by increasing demands from rising population and a changing climate, which may be alleviated through development of genetically improved crop cultivars. Research into increasing photosynthetic energy conversion efficiency has proposed many strategies to improve production but have yet to yield real-world solutions, largely because of a phenotyping bottleneck. Partial least squares regression (PLSR) is a statistical technique that is increasingly used to relate hyperspectral reflectance to key photosynthetic capacities associated with carbon uptake (maximum carboxylation rate of Rubisco, Vc,max) and conversion of light energy (maximum electron transport rate supporting RuBP regeneration, Jmax) to alleviate this bottleneck. However, its performance varies significantly across different plant species, regions, and growth environments. Thus, to cope with the heterogeneous performances of PLSR, this study aims to develop a new approach to estimate photosynthetic capacities. A framework was developed that combines six machine learning algorithms, including artificial neural network (ANN), support vector machine (SVM), least absolute shrinkage and selection operator (LASSO), random forest (RF), Gaussian process (GP), and PLSR to optimize high-throughput analysis of the two photosynthetic variables. Six tobacco genotypes, including both transgenic and wild-type lines, with a range of photosynthetic capacities were used to test the framework. Leaf reflectance spectra were measured from 400 to 2500 nm using a high-spectral-resolution spectroradiometer. Corresponding photosynthesis vs. intercellular CO2 concentration response curves were measured for each leaf using a leaf gas-exchange system. Results suggested that the mean R2 value of the six regression techniques for predicting Vc,max (Jmax) ranged from 0.60 (0.45) to 0.65 (0.56) with the mean RMSE value varying from 47.1 (40.1) to 54.0 (44.7) μmol m-2 s-1. Regression stacking for Vc,max (Jmax) performed better than the individual regression techniques with increases in R2 of 0.1 (0.08) and decreases in RMSE by 4.1 (6.6) μmol m-2 s-1, equal to 8% (15%) reduction in RMSE. Better predictive performance of the regression stacking is likely attributed to the varying coefficients (or weights) in the level-2 model (the LASSO model) and the diverse ability of each individual regression technique to utilize spectral information for the best modeling performance. Further refinements can be made to apply this stacked regression technique to other plant phenotypic traits.

Utilizing Flood Inundation Observations to Obtain Floodplain Topography in Data-Scarce Regions

Flood models predict inundation extents, and can be an important source of information for flood risk studies. Accurate flood models require high resolution and high accuracy digital elevation models (DEM); current global DEMs do not capture the topographic details in floodplains, and this often leads to inaccurate prediction of flood extents by flood models. Flood extents obtained from remotely sensed data provide indirect information about topography. Here, we attempt to use this information along with model predictions to produce better floodplain topography. The algorithm we describe is a two-step process: first, we reduce the noise along the observed flood boundaries for all particles. Then, the model predictions from these modified DEMs are assimilated with observations using a particle batch smoother. We implemented the algorithm for a synthetic test case. For the nominal case, we observed a significant improvement in accuracy in terms of RMSE (35% reduction), bias (20%) and standard deviation (40%). We conducted sensitivity analysis by using priors of varying bias (0.5 m, 1 m, 2 m) and standard deviation (1 m, 2 m, 4 m). The bias reduced to ~0.5 m or below in all the cases: the reduction in bias varied from 11% to 76%. The standard deviation of errors in the final estimate was almost half of the prior: the reduction varied from 40% to 49%. The reduction in RMSE ranged between 35% and 67%. For the case with 2 m bias and 4 m standard deviation (SRTM-like error levels), bias went down to 0.48 m (76% reduction), and standard deviation reduced to 2.24 m (44% reduction). Flood inundation maps produced from the final estimate DEMs also improved on its prior. For the 2 m bias cases, true positive rate (TPR) for peak inundation went from ~30% to more than 57% in all three cases. The algorithm produces promising results, and this type of analysis can be performed in data-poor floodplains where high resolution DEMs do not exist.