Search NASA⌕ Search

SEARCH · Search NASA

Results for “RMSE”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records
All sourcesNASA NTRSDOE OSTI
NASA NTRS2017

Biomass Retrieval from L-Band Polarimetric UAVSAR Backscatter and PRISM Stereo Imagery

The forest above-ground biomass (AGB) and spatial distribution of vegetation elements have profound effects on the productivity and biodiversity of terrestrial ecosystems. In this paper, we evaluated biomass estimation from L-band Synthetic Aperture Radar (SAR) data acquired by National Aeronautics and Space Administration (NASA) Uninhabited Aerial Vehicle SAR (UAVSAR) and the improvement of accuracy by adding canopy height information derived from stereo imagery acquired by Japan Aerospace Exploration Agency (JAXA) Panchromatic Remote Sensing Instrument for Stereo Mapping (PRISM) on-board the Advanced Land Observing Satellite (ALOS). Various models for prediction of forest biomass from UAVSAR data were investigated at pixel sizes of 1/4 ha (50 m x 50 m) and 1 ha. The variance inflation factor (VIF) was calculated for each of the explanatory variables in multivariable regression models to assess the multi-collinearity between explanatory variables. In addition, the t-and p-values were used to interpret the significance of the coefficients of each explanatory variables. The R(exp. 2), Root Mean Square Error (RMSE), bias and Akaike information criterion (AIC), and leave-one-out cross-validation (LOOCV) and bootstrapping were used to validate models. At 1/4-ha scale, the R(exp. 2) and RMSE of biomass estimation from a model using a single track of polarimetric UAVSAR data were 0.59 and 52.08 Mg/ha. With canopy height from PRISM as additional independent variable, R(exp. 2) increased to 0.76 and RMSE decreased to 39.74 Mg/ha (28.24%). At 1-ha scale, the RMSE of biomass estimation based on UAVSAR data of a single track was 39.42 Mg/ha with a R(exp. 2) of 0.77. With the canopy height from PRISM, R(exp. 2) increased to 0.86 and RMSE decreased to 29.47 Mg/ha (20.18%). The models using UAVSAR data alone underestimated biomass at levels above approximately 150 Mg/ha showing the saturation phenomenon. Adding canopy height from PRISM stereo imagery significantly improved the biomass estimation and elevated the saturation level in estimating biomass. Combined use of UAVSAR data acquired from opposite directions (odd and even tracks) slightly improved the biomass estimation.Combined use of UAVSAR data acquired from opposite directions (odd and even tracks) slightly improved the biomass estimation at 1/4-ha scale, R(exp. 2) increased from 0.59 to 0.66 and RMSE reduced from 52.08 to 48.57 Mg/ha. Averaging multiple acquisitions of UAVSAR data from the same look azimuth direction did not improve biomass estimation. A biomass map derived from NASA's LVIS (Laser Vegetation Imaging System) wave-form data was used as a reference for evaluation of the biomass maps from these models. The study has also shown that the errors decreased when deciduous, evergreen, and mixed forests were modeled separately but the improvement was not significant

Zhang, Zhiyu↗
NASA NTRS2020

Regional Tropical Aboveground Biomass Mapping with L-Band Repeat-Pass Interferometric Radar, Sparse Lidar, and Multiscale Superpixels

We introduce a multiscale superpixel approach that leverages repeat-pass interferometric coherence and sparse AGB estimates from a simulated spaceborne lidar in order to extend the NISAR mission’s applicable range of aboveground biomass (AGB) in tropical forests. Airborne and spaceborne L-band radar and full-waveform airborne lidar data are used to simulate the NISAR and GEDI mission, respectively. In addition to UAVSAR data, we use spaceborneALOS-2/PALSAR-2 imagery with 14-day temporal baseline, which is comparable to NISAR’s 12-daybaseline. Our reference AGB maps are derived from the airborne LVIS data during the AfriSAR campaign for three sites (Mondah, Ogooue, and Lope). Each tropical site has mean AGB of at least 125 Mg/ha in addition to areas with AGB exceeding 700 Mg/ha. Spatially sampling from these LVIS-derived AGB reference maps, we approximate GEDI AGB estimates. To evaluate our methodology, we perform several different analyses. First, we partition each study site into low(≤100 Mg/ha) and high (>100 Mg/ha) AGB areas, in conformity with the NISAR mission requirement to provide AGB estimates for forests between 0 and 100 Mg/ha with a RMSE below 20 Mg/ha. In the low AGB areas, this RMSE requirement is satisfied in Lope and Mondah and it fell short of the requirement in Ogooue by less 3 Mg/ha with UAVSAR and 6 Mg/ha with PALSAR-2. We note that our maps have finer spatial resolution (50 m) than NISAR requires (1 hectare). In the high AGB areas, the normalized RMSE increases to 51% (i.e.,<90 Mg/ha), but with negligible bias for all three sites. Second, we train a single model to estimate AGB across both high and low AGB regimes simultaneously and obtain a normalized RMSE that is<60% (or<100 Mg/ha). Lastly, we show the use of both (a) multiscale superpixels and (b) interferometric coherence significantly improves the accuracy of the AGB estimates. The InSAR coherence improved the RMSE by approximately 8% at Mondah with both sensors, lowering the RMSE from 59 Mg/ha to 47.4 Mg/h with UAVSAR and from 57.1 Mg/ha to 46 Mg/ha. This work illustrates one of the numerous synergistic relationships between the spaceborne lidars, such as GEDI, with L-band SAR, such as PALSAR-2 and NISAR, in order to produce robust regional AGB in high biomass tropical regions.

NISAR↗
NASA NTRS2021

Comparison of soil dielectric mixing models for Soil Moisture Retrieval using SMAP Brightness Temperature over croplands in India

The accurate estimation of soil moisture (SM) using microwave remote sensing depends mostly on careful selection of retrieval parameters among which the soil dielectric mixing model is the important one. These models are often categorized into empirical, semi-empirical or volumetric based on their methodologies and input data requirements. To study in detail, the comparative performance of four dielectric mixing models -- Wang & Schmugge model, Hallikainen model, Dobson model and Mironov model were used with Soil Moisture Active Passive (SMAP) L-band brightness temperature and Single Channel Algorithm for SM retrieval over agricultural landscapes in India. The highest performance statistics combination in terms of Root Mean Square Error (RMSE), correlation coefficient (R^(2)) and percentage bias (PBIAS) against the concurrent in-situ SM measurements were calculated at the selected validation sites. The overall results indicate that the best performance was given by the Mironov model (RMSE = 0.07 cu. m/cu. m), followed by Wang & Schmugge model (RMSE = 0.08 cu. m3/cu. m), Hallikainen model (RMSE = 0.09 cu. m/cu. m), Dobson model (RMSE = 0.10 cu. m/cu. m) and original SMAP radiometer SM (RMSE = 0.12 cu. m/cu. m). Findings of this study provides important insights into application and performance of dielectric mixing models in mapping surface SM variations. This study also underlines the pivotal role of local conditions for SM retrieval which should be carefully included in the algorithms.

Swati Suman↗
DOE OSTI2025

A Near-Real-Time Model for Predicting Electricity Disruptions in Texas During Winter Storms

There has been an increase in extreme weather events, posing a threat to power grid systems, potentially influenced by factors such as population growth, changes in ecosystems, land cover, and land use in the service area, as well as the growth of certain vegetation types. This research seeks to develop a predictive model to mitigate potential damages caused by future winter storms. This research utilizes the Light Gradient Boosting Machine (LightGBM), incorporating the number of power outages experienced at the county level, geographic details, weather information, and lagged outage and lagged weather data. The developed models were broadly divided into two groups, with six models in each group - one group without optimization and another with optimization, totaling 12 trained models. For model optimization, Bayesian optimization was employed using Root Mean Squared Error (RMSE) as the objective function. In results, when comparing Group 2 (the optimized group) with Group 1 (the non-optimized group), it was found that optimization did not always lead to a reduction in RMSE and Mean Absolute Error (MAE). However, in terms of Mean Directional Accuracy (MDA), while all results in Group 1 were below the baseline accuracy of 0.33, all results in Group 2 exceeded 0.33, with some cases showing an increase of more than three times the baseline. The results indicated that, in the optimized model group, Population and Pressure were the most influential factors when using current weather data and geographical information. When using lagged data, lagged recorded outages and lagged Pressure emerged as the most significant factors. Among the 12 developed models, the L-1-2-O model showed the lowest RMSE and MAE, as well as the highest accuracy, with values of 390.62 households and 168.13 households, respectively. To normalize the RMSE and MAE values, each metric was divided by the average number of households among the counties in Texas. For the L-1-2-O model, the scaled RMSE was 0.88% and the scaled MAE was 0.38%. In terms of MDA, which indicates the accuracy of the prediction direction, the L-1-O model achieved the highest score of 0.41. Although this study focused on Texas, which suffered the greatest impact from the winter storms in 2021, with additional validation, the methodology used in this research could be applied to other regions.

Lee, Jangjae [Texas A & M Univ., College Station, ↗
DOE OSTI2020

One-Step Ahead Prediction of Thermal Mixing Tee Sensors with Long Short Term Memory (LSTM) Neural Networks

High-temperature advanced reactors under development, such as sodium fast reactors (SFR) and molten salt cooled reactors (MSCR), are expected to offer lower levelized cost of energy (LCOE) compared to existing light water reactor (LWR’s). In the existing light water reactors (LWR’s), operation and maintenance (O&M) expenses constitute the largest fraction of the total operating cost. Some of the O&M costs are related maintenance of sensors which can fail due to exposure to harsh environment in a reactor. The O&M costs of Advanced Reactor (AR)’s are expected to constitute a significant fraction of the total cost as well, because of high temperature and radiation level in AR are likely to cause material fatigue and premature failure of sensors and components. The O&M costs in AR’s could be reduced through integration of advanced informatics of performance-related sensors into a digital twin designed for reactor monitoring. For example, machine learning (ML) could be employed for real-time validation and correction of performance-related sensors, and reducing the number of performance-related physical sensor units through virtual sensing. As part of the effort, we investigate real-time validation of thermal hydraulic sensors through one-step ahead forecasting of sensor values using long short-term memory (LSTM) recurrent neural networks (RNN). The sensors are installed in a flow loop containing a thermal mixing tee, which is a common experimental model to study thermal fatigue in a thermal hydraulic loop. In addition, nonlinear transients generated in a thermal mixing tee constitute a good challenge data set for training and validation of ML algorithms. Sensors in this study include thermocouples, flow meters, and optical fibers for distributed temperature sensing. In one experiment, measurement data sets were obtained for a loop was filled with water, and in another experiment, measurements were performed on a loop filled with liquid metal Galinstan. We have also conducted preliminary investigation of one-step ahead prediction of fiber optics-based distributed temperature sensing with LSTM networks. In predicting fiber-based temperature measurements, we treated each gauge pitch of the fiber as an independent sensor. Accuracy of one-step ahead forecasting was estimated by calculating root mean square error (RMSE) for the test segment of time series of each sensor. RMSE’s for temperature sensors in water loop were, for the most part, lower than for the same sensors in Galinstan loop. The RMSE’s for flow meters were similar for both loops. The RMSE’s for distributed temperature measured with the fiber optic sensor were similar to those of the point sensors. Results of this study demonstrated the capability of LSTM one-step ahead forecasting with RMSE comparable to uncertainty in sensor measurements.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
NASA NTRS2014

Estimation of Crop Gross Primary Production (GPP): I. Impact of MODIS Observation Footprint and Impact of Vegetation BRDF Characteristics

Accurate estimation of gross primary production (GPP) is essential for carbon cycle and climate change studies. Three AmeriFlux crop sites of maize and soybean were selected for this study. Two of the sites were irrigated and the other one was rainfed. The normalized difference vegetation index (NDVI), the enhanced vegetation index (EVI), the green band chlorophyll index (CIgreen), and the green band wide dynamic range vegetation index (WDRVIgreen) were computed from the moderate resolution imaging spectroradiometer (MODIS) surface reflectance data. We examined the impacts of the MODIS observation footprint and the vegetation bidirectional reflectance distribution function (BRDF) on crop daily GPP estimation with the four spectral vegetation indices (VIs - NDVI, EVI, WDRVIgreen and CIgreen) where GPP was predicted with two linear models, with and without offset: GPP = a × VI × PAR and GPP = a × VI × PAR + b. Model performance was evaluated with coefficient of determination (R2), root mean square error (RMSE), and coefficient of variation (CV). The MODIS data were filtered into four categories and four experiments were conducted to assess the impacts. The first experiment included all observations. The second experiment only included observations with view zenith angle (VZA) ≤ 35◦ to constrain growth of the footprint size,which achieved a better grid cell match with the agricultural fields. The third experiment included only forward scatter observations with VZA ≤ 35◦. The fourth experiment included only backscatter observations with VZA ≤ 35◦. Overall, the EVI yielded the most consistently strong relationships to daily GPP under all examined conditions. The model GPP = a × VI × PAR + b had better performance than the model GPP = a × VI × PAR, and the offset was significant for most cases. Better performance was obtained for the irrigated field than its counterpart rainfed field. Comparison of experiment 2 vs. experiment 1 was used to examine the observation footprint impact whereas comparison of experiment 4 vs. experiment 3 was used to examine the BRDF impact. Changes in R2, RMSE,CV and changes in model coefficients "a" and "b" (experiment 2 vs. experiment 1; and experiment 4 vs. experiment 3) were indicators of the impacts. The second experiment produced better performance than the first experiment, increasing R2 (↑0.13) and reducing RMSE (↓0.68 g C m−2 d−1) and CV (↓9%). For each VI, the slope of GPP = a × VI × PAR in the second experiment for each crop type changed little while the slope and intercept of GPP = a × VI × PAR + b varied field by field. The CIgreen was least affected by the MODIS observation footprint in estimating crop daily GPP (R2, ↑0.08; RMSE, ↓0.42 g C m−2 d−1; and CV, ↓7%). Footprint most affected the NDVI (R2, ↑0.15; CV, ↓10%) and the EVI (RMSE, ↓0.84 g C m−2 d−1). The vegetation BRDF impact also caused variation of model performance and change of model coefficients. Significantly different slopes were obtained for forward vs. backscatter observations, especially for the CIgreen and the NDVI. Both the footprint impact and the BRDF impact varied with crop types, irrigation options, model options and VI options.

Chlorophyll↗
NASA NTRS2020

Spatiotemporal Characteristics of the Association between AOD and PM over the California Central Valley

Many air pollution health effects studies rely on exposure estimates of particulate matter (PM) concentrations derived from remote sensing observations of aerosol optical depth (AOD). Simple but robust calibration models between AOD and PM are therefore important for generating reliable PM exposures. We conduct an in-depth examination of the spatial and temporal characteristics of the AOD-PM2.5 relationship by leveraging data from the Distributed Regional Aerosol Gridded Observation Networks (DRAGON) field campaign where eight NASA Aerosol Robotic Network (AERONET) sites were co-located with EPA Air Quality System (AQS) monitoring sites in California’s Central Valley from November 2012 to April 2013. With this spatiotemporally rich data we found that linear calibration models (R(exp 2) = 0.35, RMSE = 10.38 µg/cu.m) were significantly improved when spatial (R(exp 2) = 0.45, RMSE = 9.54 µg/cu.m), temporal (R(exp 2) = 0.62, RMSE = 8.30 µg/cu.m), and spatiotemporal (R(exp 2) = 0.65, RMSE = 7.58 µg/cu.m) functions were included. As a use-case we applied the best spatiotemporal model to convert space-borne MultiAngle Imaging Spectroradiometer (MISR) AOD observations to predict PM2.5 over the region (R(exp 2) = 0.60, RMSE = 8.42 µg/cu.m). Our results imply that simple AERONET AOD-PM2.5 calibrations are robust and can be reliably applied to space-borne AOD observations, resulting in PM2.5 prediction surfaces for use in downstream applications.

Meytar Sorek-Hamer↗
NASA NTRS2022

Optimizing Landsat Next Shortwave Infrared Bands for Crop Residue Characterization

This study focused on optimizing the placement of shortwave infrared (SWIR) bands for pixel-level estimation of fractional crop residue cover (f R ) for the upcoming Landsat Next mission. We applied an iterative wavelength shift approach to a database of crop residue field spectra collected in Beltsville, Maryland, USA (n = 916) and computed generalized two- and three-band spectral indices for all wavelength combinations between 2000 and 2350 nm, then used these indices to model field-measured f R . A subset of the full dataset with a Normalized Difference Vegetation Index (NDVI) < 0.3 threshold (n = 643) was generated to evaluate green vegetation impacts on f R estimation. For the two-band wavelength shift analyses applied to the NDVI < 0.3 dataset, a generalized normalized difference using 2226 nm and 2263 nm bands produced the top f R estimation performance (R 2 = 0.8222; RMSE = 0.1296). These findings were similar to the established two-band Shortwave Infrared Normalized Difference Residue Index (SINDRI) (R 2 = 0.8145; RMSE = 0.1324). Performance of the two-band generalized normalized difference and SINDRI decreased for the full-NDVI dataset (R 2 = 0.5865 and 0.4144, respectively). For the three-band wavelength shift analyses applied to the NDVI < 0.3 dataset, a generalized ratio-based index with a 2031–2085–2216 nm band combination, closely matching established Cellulose Absorption Index (CAI) bands, was top performing (R 2 = 0.8397; RMSE = 0.1231). Three-band indices with CAI-type wavelengths maintained top f R estimation performance for the full-NDVI dataset with a 2036–2111–2217 nm band combination (R 2 = 0.7581; RMSE = 0.1548). The 2036–2111–2217 nm band combination was also top performing in f R estimation (R 2 = 0.8690; RMSE = 0.0970) for an additional analysis assessing combined green vegetation cover and surface moisture effects. Our results indicate that a three-band configuration with band centers and wavelength tolerances of 2036 nm (±5 nm), 2097 nm (±14 nm), and 2214 (±11 nm) would optimize Landsat Next SWIR bands for f R estimation.

Landsat Next↗
NASA NTRS2014

Assimilation of Freeze - Thaw Observations into the NASA Catchment Land Surface Model

The land surface freeze-thaw (F-T) state plays a key role in the hydrological and carbon cycles and thus affects water and energy exchanges and vegetation productivity at the land surface. In this study, we developed an F-T assimilation algorithm for the NASA Goddard Earth Observing System, version 5 (GEOS-5) modeling and assimilation framework. The algorithm includes a newly developed observation operator that diagnoses the landscape F-T state in the GEOS-5 Catchment land surface model. The F-T analysis is a rule-based approach that adjusts Catchment model state variables in response to binary F-T observations, while also considering forecast and observation errors. A regional observing system simulation experiment was conducted using synthetically generated F-T observations. The assimilation of perfect (error-free) F-T observations reduced the root-mean-square errors (RMSE) of surface temperature and soil temperature by 0.206 C and 0.061 C, respectively, when compared to model estimates (equivalent to a relative RMSE reduction of 6.7 percent and 3.1 percent, respectively). For a maximum classification error (CEmax) of 10 percent in the synthetic F-T observations, the F-T assimilation reduced the RMSE of surface temperature and soil temperature by 0.178 C and 0.036 C, respectively. For CEmax=20 percent, the F-T assimilation still reduces the RMSE of model surface temperature estimates by 0.149 C but yields no improvement over the model soil temperature estimates. The F-T assimilation scheme is being developed to exploit planned operational F-T products from the NASA Soil Moisture Active Passive (SMAP) mission.

GEOS5↗
DOE OSTI2023

Self-diagnosis of model suitability for continuous measurements of stream-dissolved organic carbon derived from in situ UV–visible spectroscopy

Application of high-frequency monitoring of dissolved organic carbon (DOC) is difficult in instances where training datasets are challenging to develop (e.g., remote locations) and the relationship between optical features and DOC concentration changes due to environmental or landscape shifts (e.g., climate or land-use change). We developed and compared three partial least squares (PLS) models using in situ water level measurements, conductivity, and UV–Vis spectral attenuation to predict DOC. Two site-specific models were developed using data from a hillslope-dominated forest or a low-relief wetland-pond-dominated stream catchment. The third model, using data from both sites, exhibited the best performance (DOC range = 4–15.5 mg C L −1 , mean = 8.38 mg C L −1 , training RMSE = 0.34 mg C L −1 , internal validation RMSE = 0.50 mg C L −1 , external validation RMSE = 2.43 mg C L −1 ). We further demonstrate using PLS model statistics to monitor performance and elucidate when and how models should be updated. These statistics, Hotelling's T 2 and squared prediction errors, are useful consistency checks for the predictions made and detect underlying inconsistencies that, if undetected, can reduce the robustness of DOC prediction. For example, via the T 2 statistic, we identified the summer–autumn transition as a period when DOC composition differed from what was represented in the training dataset. We also determined that elevated SUVA 254 values contributed to the overall bias observed in predictions made during the subsequent year as part of the external validation. This enabled the application of a bias correction that reduced the RMSE from 2.43 to 0.89 mg C L −1 . The method presented here could be applied to future monitoring programs enabling model updates to monitor DOC fluxes accurately from optical datasets (e.g., attenuance or fluorescence) in the face of developing datasets in remote locations or environmental change. In conclusion, implementation of this approach may also identify possible regime shifts or landscape and hydrologic change associated with climate and other environmental changes relevant to terrestrial to aquatic fluxes.

UV-VIS spectroscopy↗
DOE OSTI2021

Daily grass reference evapotranspiration with Meteosat Second Generation shortwave radiation and reference ET products

Here we assess the accuracy of estimating daily grass reference evapotranspiration (PM-ET o ) using daily shortwave radiation (R s ) and reference evapotranspiration (ET REF ) products provided by the Meteosat Second Generation (MSG) geostationary satellite delivered by the Satellite Applications Facility on Land Surface Analysis (LSA-SAF) framework. The accuracy of using reanalysis ERA5 shortwave radiation data (R s ERA5 ) provided by the European Center for Medium-Range Weather Forecasts (ECMWF) is also evaluated. The assessments were performed using observed weather variables at 37 weather stations distributed across continental Portugal, where climate conditions range from semi-arid to humid, and 12 weather stations located in Azores islands, characterized by humid, windy and often cloudy conditions. This study&#x27;s use of data from a variety of climate conditions contributed to a unique and innovative assessment of the usability of LSA-SAF and ERA5 products for ET o estimation. The first assessment focused on comparing LSA-SAF estimates of R s (R s LSA-SAF ) against ground stations (R s ground ). The results showed a good matching between the two R s data sets for continental Portugal but a tendency for R s LSA-SAF to under-estimate R s ground in the cloudy islands of Azores. ET o values computed using R s LSA-SAF data and observed temperature, humidity and wind speed (ET o LSA-SAF ) were then compared with PM-ET o estimates with ground-based data, which were used as benchmark; input data of temperature and humidity needed for PM-ET o were quality checked for surface aridity effects. It was observed that ET o LSA-SAF is strongly correlated with PM-ET o (R 2 > 0.97) for most locations in continental Portugal, with regression coefficient of a linear regression forced to the origin ranging between 0.95 and 1.05, mean root mean square error (RMSE) of 0.13 mm d –1 , and Nash and Sutcliff efficiency of modeling (EF) above 0.95. For most Azores locations, ET o LSA-SAF over-estimated PM-ET o . This is likely a consequence of the high spatio-temporal heterogeneity of weather conditions that occur in these oceanic islands together with the different footprints of satellite (averaged over the pixel) and station observations. Reanalysis ERA5 shortwave radiation data presented similar behavior to the LSA-SAF products, however with slightly lower accuracy. The daily LSA-SAF ET REF product (ET REF LSA-SAF ) was assessed and results have shown a good accuracy of this product, with acceptable RMSE and high EF values, for continental Portugal but a low accuracy for the Azores islands. A simplified bias correction approach was shown to improve both ET o derived from the LSA-SAF products, namely for Azores stations, which seem to be representative of smaller areas. The use of the FAO-PM temperature approach (PMT) was also assessed using the R s LSA-SAF and R s ERA5 data, which showed a superiority of the LSA-SAF product for ET o estimations (ET o PMT LSA-SAF ). No significant differences (p < 0.05) were observed in terms of the median value of the RMSE when adopting ET o PMT and ET REF LSA-SAF . Differently, results showed that using the R s LSA-SAF in the PMT approach (ET o PMT LSA-SAF ) produces significantly better RMSE results than ET o PMT and ET REF LSA-SAF . Overall, the performed assessment allows concluding that the use of R s LSA-SAF, and to a lesser extent the use of the R s ERA5 , highly improves the accuracy of computation of ET o when R s observations are not available, including when only temperature data are accessible. The use of the ET REF LSA-SAF product is a good alternative when observed weather data are not available.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Accuracy of predictions made by machine learned models for biocrude yields obtained from hydrothermal liquefaction of organic wastes

Hydrothermal liquefaction (HTL) has potential for converting abundant wet organic wastes into renewable fuels. Because HTL consists of a complex reaction network, deterministic, physics-based prediction of its biocrude yield is prohibitively difficult. Data-driven methods provide an alternative to the physics-based approach; however, rigorous testing must be performed to ensure the accuracy of predictions made by data-driven methods. To this end, a data set was assembled consisting of 570 data points appearing in the open literature. The data set was divided into training, validation, and test sub-sets and used for evaluating different machine learning regression approaches to predict biocrude yield. Among the tested algorithms, Random Forest and eXtreme Gradient Boosting (XGBoost) predicted biocrude yields in a test set that had not been used for training with the greatest accuracy, with root mean square errors (RMSE) of 8.34 and 8.57, respectively. Further refinement of the Random Forest model reduced its RMSE to 8.07. In comparison, predictions of a series of literature models resulted in RMSE ranging from 9.16 in the most accurate case to 27.6 in the least accurate; most literature models yielded RMSE values > 10. Using biocrude yield predictions from the most accurate Random Forest model and a probabilistic economic analysis found that the model accuracy is sufficient to prioritize allocation of resources based on projected minimum fuel selling price. In our report the models and analysis represent a major advance in the ability to use readily available data to predict biocrude yields on new feedstocks that have not previously been studied.

42 ENGINEERING↗
DOE OSTI2020

Predicting lake surface water phosphorus dynamics using process-guided machine learning

Phosphorus (P) loading to lakes is degrading the quality and usability of water globally. Accurate predictions of lake P dynamics are needed to understand whole-ecosystem P budgets, as well as the consequences of changing lake P concentrations for water quality. However, complex biophysical processes within lakes, along with limited observational data, challenge our capacity to reproduce short-term lake dynamics needed for water quality predictions, as well as long-term dynamics needed to understand broad scale controls over lake P. Here we use an emerging paradigm in modeling, process-guided machine learning (PGML), to produce a phosphorus budget for Lake Mendota (Wisconsin, USA) and to accurately predict epilimnetic phosphorus over a time range of days to decades. In our implementation of PGML, which we term a Process-Guided Recurrent Neural Network (PGRNN), we combine a process-based model for lake P with a recurrent neural network, and then constrain the predictions with ecological principles. We test independently the process-based model, the recurrent neural network, and the PGRNN to evaluate the overall approach. The process-based model accounted for most of the observed pattern in lake P; however it missed the long-term trend in lake P and had the worst performance in predicting winter and summer P in surface waters. The root mean square error (RMSE) for the process-based model, the recurrent neural network, and the PGRNN was 33.0 μg P L -1 , 22.7 μg P L -1 , and 20.7 μg P L -1 , respectively. All models performed better during summer, with RMSE values for the three models (same order) equal to 14.3 μg P L -1 , 10.9 μg P L -1 , and 10.7 μg P L -1 . Although the PGRNN had only marginally better RMSE during summer, it had lower bias and reproduced long-term decreases in lake P missed by the other two models. For all seasons and all years, the recurrent neural network had better predictions than process alone, with root mean square error (RMSE) of 23.8 μg P L -1 and 28.0 μg P L -1 , respectively. The output of PGRNN indicated that new processes related to water temperature, thermal stratification, and long term changes in external loads are needed to improve the process model. By using ecological knowledge, as well as the information content of complex data, PGML shows promise as a technique for accurate prediction in messy, real-world ecological dynamics, while providing valuable information that can improve our understanding of process.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

A novel approach to increase accuracy in remotely sensed evapotranspiration through basin water balance and flux tower constraints

Remote sensing-derived evapotranspiration (RSET) products capture the spatiotemporal variations of evapotranspiration (ET) from field to basin scales with unprecedented details. However, their accuracy varies across RSET estimation methods and diverse hydroclimate regions. While ET modeling efforts to account for biophysical processes and controlling parameters have made good progress in recent years, a parallel approach of integrating in-situ ET with RSET could reduce biases in RSET products. Basin water balance ET (WBET) and flux tower ET are widely applied to evaluate RSET accuracy, yet such ET measurements are rarely used for RSET bias corrections, especially for large area applications. To address this issue, we propose a novel approach: the water balance equivalence (WABE) method, which generates spatially continuous WBET for correcting biases in RSET products. The WABE method computes synthetic WBET by integrating observed WBET and flux tower-derived FLUXCOM ET, which fills the spatial gaps of observed WBET and generates a spatially continuous WBET dataset. Synthetic WBET (2002–2015 annual average) of eight-digit hydrologic unit code (HUC8) basins across the conterminous United States (CONUS), constituting 44 % (887 out of 2035 basins) of CONUS basins, was determined within 2.0 % (RMSE = 12 %) of observed WBET at CONUS and between 1–12 % (RMSE = 3–33 %) across 18 regions in CONUS. With WABE-based bias corrections, the overall annual bias of RSET decreased from 10 % (RMSE = 34 %) to 6 % (RMSE = 26 %) across 37 flux tower sites. The WABE method offers a new approach for RSET accuracy improvement and shows great promise for large area implementations with a potential to yield substantial benefits for building accurate basin water budgets and water management decisions.

Khand, Kul↗
DOE OSTI2023

The underappreciated importance of solar radiation in constraining spring phenology of temperate ecosystems in the Northern and Eastern United States

Spring phenology of temperate ecosystems is highly sensitive to climate change, generating various impacts on many important terrestrial surface biophysical processes. Although various prognostic models relying on environmental variables of temperature and photoperiod have been developed for spring phenology, comprehensive ecosystem-scale evaluations over large landscapes and long-time periods remain lacking. Further, environmental variables other than temperature and photoperiod might also importantly constrain spring phenology modelling but remain under-investigation. To address these issues, we leveraged around 20-years datasets of environmental variables (from Daymet and GLDAS products) and the spring phenology metric (i.e., the greenup date) respectively derived from MODIS and PhenoCams across 108 sites in the Northern and Eastern United States. We firstly cross-compared MODIS-derived greenup date with official PhenoCams product with high accuracy (R 2 = 0.70). Then, we evaluated the three prognostic models (i.e., Growing Degree Date (GDD), Sequential (SEQ) and optimality-based (OPT)) with MODIS-derived spring phenology, assessed the model residuals and their associations with soil moisture, rainfall, and solar radiation, and revised the two photoperiod-relevant models (SEQ, OPT) by replacing the daylength variable with solar radiation, which was found to contribute the most to model residuals. We found that 1) all models demonstrated good capability in characterizing spring phenology, with OPT performing the best (RMSE = 8.04 ± 5.05 days), followed by SEQ (RMSE = 10.57 ± 7.77 days) and GDD (RMSE = 10.84 ± 8.42 days), 2) all models displayed high model residuals showing tight correlation with solar radiation (r = 0.45–0.75), and 3) the revised models that included solar radiation significantly performed better with an RMSE reduction by 22.08%. Such results are likely because solar radiation better constrains early growing season plant photosynthesis than photoperiod, supporting the hypothesis of spring phenology as an adaptive strategy to maximize photosynthetic carbon gain (approximated by solar radiation) while minimizing frost damage risk (captured by temperature). Collectively, our study here reveals the underappreciated importance of solar radiation in constraining spring phenology of temperate ecosystems, and suggests ways to improve spring phenology modelling and other phenology-related ecological processes.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Ensemble methods for quantification of potassium oxide in ChemCam Mars and laboratory spectra

In this paper we test new approaches for predicting the amount of element oxides in rock samples from the ChemCam instrument suite onboard the NASA Curiosity rover by focusing on K 2 O. Using the expanded dataset compiled by Gasda et al. (2021) with and without the Earth to Mars (E2M and NoE2M) transformation discussed in Clegg et al. (2017) we trained blended submodels using the “double blending” technique and compared these to ensemble methods (Random Forest, ExtraTrees, and Gradient Boosting Regression). We found that ensemble methods performed similar to blended submodels when looking at RMSE-P on the laboratory spectra and provided significant advantages when looking at spectra coming from Mars. For the full model, blended submodels achieved an RMSE-P of 0.62 and 0.60 (E2M and NoE2M respectively) while Gradient Boosting Regression resulted in a slightly improved RMSE-P of 0.59 and 0.60. More importantly, by employing a local RMSE-P estimation technique where model performance is evaluated based on nearby test samples we found that using ensemble methods can lower the quantification limit for K 2 O from the current value of ≈0.6 wt% to ≈0.08 wt% using Extra Trees and Random Forest. This would allow for a much larger range of K 2 O values to be quantified on Mars with greater certainty given that most targets seen on Mars tend to have <1 wt% K2O. Finally, we used both Mean Decrease in Impurity (MDI) and permutation importance techniques to investigate the wavelengths used by the ensemble methods and found that they correspond to known potassium emission lines. This suggests that ensemble methods can provide an easier to train and improved alternative to blended submodels for predicting potassium compositions from Laser Induced Breakdown Spectroscopy (LIBS) data.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Enhanced Boundary Layer Height Detection Using Ceilometer, Surface Meteorology, and Radiation Products With a Random Forest Ensemble Method

This study develops and evaluates a Random Forest (RF) model for estimating planetary boundary layer height (PBLH) using 9 years of data from the Atmospheric Radiation Measurement Southern Great Plains (ARM SGP) user facility, with potential application in the NOAA Surface Radiation (SURFRAD) Network. The model integrates ceilometer, surface meteorology, and radiation measurements, and is trained using thermodynamic PBLH estimates derived from radiosondes. This approach aims to bridge gaps between aerosol-based and thermodynamic-based PBLH estimates. The RF model outperformed traditional methods during daytime and better captured transition periods, demonstrating improved accuracy and robustness. At ARM SGP, it showed a substantial reduction in both bias and RMSE, with a bias near zero (−4.9 m) compared with traditional Haar Wavelet (HW) (70.9 m) and Vaisala BL-View software (124.1 m), and an RMSE of 303.2 m, lower than both BL-View (566.9 m) and HW (404.6 m). During daytime hours, RF consistently outperformed both alternatives, maintaining lower bias and RMSE across all periods. At a second evaluation site, RF achieved the lowest overall RMSE (323.7 m), similar to HW (326.4 m) and significantly better than BL-View (738.3 m). However, all models showed reduced accuracy under stable nighttime conditions, limiting the reliability of PBLH estimates. Key predictors for the model included the lifting condensation level height (LCLH), aerosol gradients, and month for seasonal variability. The study underscores the potential of integrating machine learning with multiple data sets such as surface energy and thermodynamic data to advance PBLH estimation.

boundary layer height↗
DOE OSTI2020

Cross-Market Price Difference Forecast Using Deep Learning for Electricity Markets

Price forecasting is in the center of decision making in electricity markets. Many researches have been done in forecasting energy prices while little research has been reported on forecasting price difference between day-ahead and realtime markets due to its high volatility, which however plays a critical role in virtual trading. To this end, this paper takes the first attempt to employ novel deep learning architecture with Bidirectional Long-Short Term Memory (LSTM) units to forecast the price difference between day-ahead and real-time markets for the same node. The raw data is collected from PJM market, processed and fed into the proposed network. The Root Mean Squared Error (RMSE) and customized performance metric are used to evaluate the performance of the proposed method. Case studies show that it outperforms the traditional statistical models like ARIMA, and machine learning models like XGBoost and SVR methods in both RMSE and the capability of forecasting the sign of price difference. Additionally, to cross-market price difference forecast, the proposed approach has the potential to be applied to solve other forecasting problems such as price spread forecast in DA market for Financial Transmission Right (FTR) trading purpose.

DA/RT price difference↗