scholarly journals Machine learning estimates of eddy covariance carbon flux in a scrub in the Mexican highland

2021 ◽  
Vol 18 (2) ◽  
pp. 367-392
Author(s):  
Aurelio Guevara-Escobar ◽  
Enrique González-Sosa ◽  
Mónica Cervantes-Jiménez ◽  
Humberto Suzán-Azpiri ◽  
Mónica Elisa Queijeiro-Bolaños ◽  
...  
Keyword(s):  
Machine Learning ◽  
Eddy Covariance ◽  
Carbon Sink ◽  
Ecosystem Respiration ◽  
Gross Primary Production ◽  
Model Performance ◽  
Net Ecosystem Exchange ◽  
Carbon Dynamics ◽  
Ordinary Least Squares ◽  
Machine Learning Algorithms

Abstract. Arid and semiarid ecosystems contain relatively high species diversity and are subject to intense use, in particular extensive cattle grazing, which has favored the expansion and encroachment of perennial thorny shrubs into the grasslands, thus decreasing the value of the rangeland. However, these environments have been shown to positively impact global carbon dynamics. Machine learning and remote sensing have enhanced our knowledge about carbon dynamics, but they need to be further developed and adapted to particular analysis. We measured the net ecosystem exchange (NEE) of C with the eddy covariance (EC) method and estimated gross primary production (GPP) in a thorny scrub at Bernal in Mexico. We tested the agreement between EC estimates and remotely sensed GPP estimates from the Moderate Resolution Imaging Spectroradiometer (MODIS), and also with two alternative modeling methods: ordinary-least-squares (OLS) regression and ensembles of machine learning algorithms (EMLs). The variables used as predictors were MODIS spectral bands, vegetation indices and products, and gridded environmental variables. The Bernal site was a carbon sink even though it was overgrazed, the average NEE during 15 months of 2017 and 2018 was −0.78 gCm-2d-1, and the flux was negative or neutral during the measured months. The probability of agreement (θs) represented the agreement between observed and estimated values of GPP across the range of measurement. According to the mean value of θs, agreement was higher for the EML (0.6) followed by OLS (0.5) and then MODIS (0.24). This graphic metric was more informative than r2 (0.98, 0.67, 0.58, respectively) to evaluate the model performance. This was particularly true for MODIS because the maximum θs of 4.3 was for measurements of 0.8 gCm-2d-1 and then decreased steadily below 1 θs for measurements above 6.5 gCm-2d-1 for this scrub vegetation. In the case of EML and OLS, the θs was stable across the range of measurement. We used an EML for the Ameriflux site US-SRM, which is similar in vegetation and climate, to predict GPP at Bernal, but θs was low (0.16), indicating the local specificity of this model. Although cacti were an important component of the vegetation, the nighttime flux was characterized by positive NEE, suggesting that the photosynthetic dark-cycle flux of cacti was lower than ecosystem respiration. The discrepancy between MODIS and EC GPP estimates stresses the need to understand the limitations of both methods.

scholarly journals Eddy covariance carbon flux in a scrub in the Mexican highland

2020 ◽  
Author(s):  
Aurelio Guevara-Escobar ◽  
Enrique González-Sosa ◽  
Mónica Cervantes-Jiménez ◽  
Humberto Suzán-Azpiri ◽  
Mónica Elisa Queijeiro-Bolaños ◽  
...  
Keyword(s):  
Primary Production ◽  
Eddy Covariance ◽  
Vegetation Index ◽  
Carbon Sink ◽  
Ecosystem Respiration ◽  
Gross Primary Production ◽  
Net Ecosystem Exchange ◽  
R Package ◽  
Dark Cycle ◽  
Remote Sensors

Abstract. Vegetation fixes C in its biomass through photosynthesis or might release it into the atmosphere through respiration. Measurements of these fluxes would help us understand ecosystem functioning. The eddy covariance technique (EC) is widely used to measure the net ecosystem exchange of C (NEE) which is the balance between gross primary production (GPP) and ecosystem respiration (Reco). Orbital satellites such as MODIS can also provide estimates of GPP. In this study, we measured NEE with the EC in a scrub at Bernal in Mexico, and then partitioned into gross primary production (GPP-EC) and Reco using the recent R package Reddyproc. Measurements of GPP-EC were related to the estimates from the MODIS satellite provided in product MOD17A2H, which contains data of the gross primary productivity (GPP-MODIS). The Bernal site was a carbon sink despite it was an overgrazed site, the average NEE during fifteen months of 2017 and 2018 was −0.78 g C m−2 d−1 and the flux was negative in all measured months. The GPP-MODIS underestimated the ground data when representing the relation with a Theil-Sen regression: GPP-EC = 1.866 + 1.861 GPP-MODIS; an ordinary less squares regression had similar coefficients and the R2 was 0.6. Although cacti (CAM), legume shrubs (C3) and herbs (C3) had a similar vegetation index, the nighttime flux was characterized by positive NEE suggesting that the photosynthetic dark-cycle flux of cacti was lower than Reco. The discrepancy among the GPP flux estimates stresses the need to understand the limitations of EC and remote sensors, while incorporating complementary monitoring and modelling schemes of nighttime Reco, particularly in the presence of species with different photosynthetic cycles.

scholarly journals Towards a standardized processing of Net Ecosystem Exchange measured with eddy covariance technique: algorithms and uncertainty estimation

2006 ◽  
Vol 3 (4) ◽  
pp. 571-583 ◽  
Author(s):  
D. Papale ◽  
M. Reichstein ◽  
M. Aubinet ◽  
E. Canfora ◽  
C. Bernhofer ◽  
...  
Keyword(s):  
Eddy Covariance ◽  
Ecosystem Respiration ◽  
Gross Primary Production ◽  
Net Ecosystem Exchange ◽  
Terrestrial Ecosystem ◽  
Climatic Conditions ◽  
High Temporal Resolution ◽  
Eddy Covariance Technique ◽  
Forest Sites ◽  
European Database

Abstract. Eddy covariance technique to measure CO2, water and energy fluxes between biosphere and atmosphere is widely spread and used in various regional networks. Currently more than 250 eddy covariance sites are active around the world measuring carbon exchange at high temporal resolution for different biomes and climatic conditions. In this paper a new standardized set of corrections is introduced and the uncertainties associated with these corrections are assessed for eight different forest sites in Europe with a total of 12 yearly datasets. The uncertainties introduced on the two components GPP (Gross Primary Production) and TER (Terrestrial Ecosystem Respiration) are also discussed and a quantitative analysis presented. Through a factorial analysis we find that generally, uncertainties by different corrections are additive without interactions and that the heuristic u*-correction introduces the largest uncertainty. The results show that a standardized data processing is needed for an effective comparison across biomes and for underpinning inter-annual variability. The methodology presented in this paper has also been integrated in the European database of the eddy covariance measurements.

scholarly journals Simulation of Carbon Exchange from a Permafrost Peatland in the Great Hing’an Mountains Based on CoupModel

Atmosphere ◽  
2021 ◽  
Vol 13 (1) ◽  
pp. 44
Author(s):  
Yue Li ◽  
Zhongmei Wan ◽  
Li Sun
Keyword(s):  
Climate Change ◽  
Carbon Sink ◽  
Ecosystem Respiration ◽  
Gross Primary Production ◽  
Net Ecosystem Exchange ◽  
Carbon Accumulation ◽  
Future Climate ◽  
Future Climate Change ◽  
Growing Seasons ◽  
Source Sink

Climate change is accelerating its impact on northern ecosystems. Northern peatlands store a considerable amount of C, but their response to climate change remains highly uncertain. In order to explore the feedback of a peatland in the Great Hing’an Mountains to future climate change, we simulated the response of the overall net ecosystem exchange (NEE), ecosystem respiration (ER), and gross primary production (GPP) during 2020–2100 under three representative concentration pathways (RCP2.6, RCP6.0, and RCP8.5). Under the RCP2.6 and RCP6.0 scenarios, the carbon sink will increase slightly until 2100. Under the RCP8.5 scenario, the carbon sink will follow a trend of gradual decrease after 2053. These results show that when meteorological factors, especially temperature, reach a certain degree, the carbon source/sink of the peatland ecosystem will be converted. In general, although the peatland will remain a carbon sink until the end of the 21st century, carbon sinks will decrease under the influence of climate change. Our results indicate that in the case of future climate warming, with the growing seasons experiencing overall dryer and warmer environments and changes in vegetation communities, peatland NEE, ER, and GPP will increase and lead to the increase in ecosystem carbon accumulation.

scholarly journals Gross Primary Production of Rainfed and Irrigated Potato (Solanum tuberosum L.) in the Colombian Andean Region Using Eddy Covariance Technique

Water ◽  
2021 ◽  
Vol 13 (22) ◽  
pp. 3223
Author(s):  
Fabio Ernesto Martínez-Maldonado ◽  
Angela María Castaño-Marín ◽  
Gerardo Antonio Góez-Vinasco ◽  
Fabio Ricardo Marin
Keyword(s):  
Leaf Area ◽  
Eddy Covariance ◽  
Carbon Sink ◽  
Ecosystem Respiration ◽  
Irrigation System ◽  
Solanum Tuberosum L ◽  
Gross Primary Production ◽  
Agricultural Drought ◽  
Area Index ◽  
Potato Crops

Potato farming is relevant for global carbon balances and greenhouse emissions, of which gross primary productivity (GPP) is one of the main drivers. In this study, the net carbon ecosystem exchange (NEE) was measured using the Eddy Covariance (EC) method in two potato crops, one of them with an irrigation system, the other under rainfed conditions. Accurate NEE partition into GPP and ecosystem respiration (RECO) was carried out by fitting a light response curve. Direct measurements of dry weight and leaf area were performed from sowing to the end of canopy life cycle and tuber bulking. Agricultural drought in the rainfed crop resulted in limited GPP rate, low leaf area index (LAI), and low canopy carbon assimilation response to the photosynthetically active radiation (PAR). Hence, in this crop, there was lower efficiency in tuber biomass gain and NEE sum indicated net carbon emissions to atmosphere (NEE = 154.7 g C m−2 ± 30.21). In contrast, the irrigated crop showed higher GPP rate and acted as a carbon sink (NEE = −366.6 g C m−2 ± 50.30). Our results show, the environmental and productive benefits of potato crops grown under optimal water supply.

A Machine Learning Approach to Upscale Net Ecosystem Exchange to a Regional Scale: Integration of Eddy Covariance, Remote Sensing and Reanalysis Data

2020 ◽  
Author(s):  
Oliver Reitz ◽  
Alexander Graf ◽  
Marius Schmidt ◽  
Gunnar Ketzler ◽  
Michael Leuchner
Keyword(s):  
Machine Learning ◽  
Land Use ◽  
High Resolution ◽  
Eddy Covariance ◽  
Catchment Area ◽  
Cross Validation ◽  
Regional Scale ◽  
Vegetation Indices ◽  
Model Performance ◽  
Net Ecosystem Exchange

<p>Net Ecosystem Exchange (NEE) is an important factor regarding the impact of land use changes to the global carbon cycle and thus climate change. The Eddy Covariance technique is the most direct way of measuring CO<sub>2</sub> fluxes, however, it provides spatially discontinuous data from a sparse network of stations. Thus, generating high-resolution spatiotemporal products of carbon fluxes remains a major challenge. Machine Learning (ML) techniques are a promising approach to upscale this information to regional and global scales and can thereby help to produce better NEE datasets for earth-system modelling.</p><p>Our approach uses statistical relationships between NEE, vegetation indices and meteorological variables to train a Random Forest model with spatial feature selection to predict daily NEE values at 1 km spatial resolution for the Rur-catchment area (ca. 2400 km²) in western Germany. Data from twelve Eddy stations of different land use types of the TERENO Network Eifel/Lower Rhine Valley between 2010 and 2018 were used to train and test the ML model. Factors potentially affecting NEE such as vegetation indices (NDVI, EVI, LAI) extracted from MODIS products, incoming solar radiation from Heliosat (SARAH-2) and additional meteorological variables from COSMO REA6 reanalysis products served as independent variables, which were further evaluated in regard to their relative importance for NEE prediction.</p><p>A novel spatial cross-validation scheme has been applied and compared to a conventional random k-fold cross-validation. This is important for the assessment of the model performance regarding spatial predictions beyond the scope of training locations in contrast to mere data reproduction. Results indicate a lower model performance evaluated with spatial cross-validation and that conventional random cross-validation hence leads to an overoptimistic view of the prediction skills. Nonetheless, the ML approach displayed a feasible way to upscale carbon fluxes to a regional scale utilizing different datasets and produced high-resolution NEE-raster for an entire catchment area.</p>

scholarly journals Predicting Future Occurrence of Acute Hypotensive Episodes Using Noninvasive and Invasive Features

2021 ◽  
Vol 186 (Supplement_1) ◽  
pp. 445-451
Author(s):  
Yifei Sun ◽  
Navid Rashedi ◽  
Vikrant Vaze ◽  
Parikshit Shah ◽  
Ryan Halter ◽  
...  
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Real World ◽  
Short Term Memory ◽  
Model Performance ◽  
Learning Technologies ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Continuous Map

ABSTRACT Introduction Early prediction of the acute hypotensive episode (AHE) in critically ill patients has the potential to improve outcomes. In this study, we apply different machine learning algorithms to the MIMIC III Physionet dataset, containing more than 60,000 real-world intensive care unit records, to test commonly used machine learning technologies and compare their performances. Materials and Methods Five classification methods including K-nearest neighbor, logistic regression, support vector machine, random forest, and a deep learning method called long short-term memory are applied to predict an AHE 30 minutes in advance. An analysis comparing model performance when including versus excluding invasive features was conducted. To further study the pattern of the underlying mean arterial pressure (MAP), we apply a regression method to predict the continuous MAP values using linear regression over the next 60 minutes. Results Support vector machine yields the best performance in terms of recall (84%). Including the invasive features in the classification improves the performance significantly with both recall and precision increasing by more than 20 percentage points. We were able to predict the MAP with a root mean square error (a frequently used measure of the differences between the predicted values and the observed values) of 10 mmHg 60 minutes in the future. After converting continuous MAP predictions into AHE binary predictions, we achieve a 91% recall and 68% precision. In addition to predicting AHE, the MAP predictions provide clinically useful information regarding the timing and severity of the AHE occurrence. Conclusion We were able to predict AHE with precision and recall above 80% 30 minutes in advance with the large real-world dataset. The prediction of regression model can provide a more fine-grained, interpretable signal to practitioners. Model performance is improved by the inclusion of invasive features in predicting AHE, when compared to predicting the AHE based on only the available, restricted set of noninvasive technologies. This demonstrates the importance of exploring more noninvasive technologies for AHE prediction.

scholarly journals Effects of experimental nitrogen deposition on peatland carbon pools and fluxes: a modelling analysis

2015 ◽  
Vol 12 (1) ◽  
pp. 79-101 ◽  
Author(s):  
Y. Wu ◽  
C. Blodau ◽  
T. R. Moore ◽  
J. Bubier ◽  
S. Juutinen ◽  
...  
Keyword(s):  
Ecosystem Respiration ◽  
Model Performance ◽  
Net Ecosystem Exchange ◽  
N Fertilization ◽  
N Deposition ◽  
Competitive Advantages ◽  
Long Term Effects ◽  
N Content ◽  
Modelling Analysis

Abstract. Nitrogen (N) pollution of peatlands alters their carbon (C) balances, yet long-term effects and controls are poorly understood. We applied the model PEATBOG to explore impacts of long-term nitrogen (N) fertilization on C cycling in an ombrotrophic bog. Simulations of summer gross ecosystem production (GEP), ecosystem respiration (ER) and net ecosystem exchange (NEE) were evaluated against 8 years of observations and extrapolated for 80 years to identify potential effects of N fertilization and factors influencing model behaviour. The model successfully simulated moss decline and raised GEP, ER and NEE on fertilized plots. GEP was systematically overestimated in the model compared to the field data due to factors that can be related to differences in vegetation distribution (e.g. shrubs vs. graminoid vegetation) and to high tolerance of vascular plants to N deposition in the model. Model performance regarding the 8-year response of GEP and NEE to N input was improved by introducing an N content threshold shifting the response of photosynthetic capacity (GEPmax) to N content in shrubs and graminoids from positive to negative at high N contents. Such changes also eliminated the competitive advantages of vascular species and led to resilience of mosses in the long-term. Regardless of the large changes of C fluxes over the short-term, the simulated GEP, ER and NEE after 80 years depended on whether a graminoid- or shrub-dominated system evolved. When the peatland remained shrub–Sphagnum-dominated, it shifted to a C source after only 10 years of fertilization at 6.4 g N m−2 yr−1, whereas this was not the case when it became graminoid-dominated. The modelling results thus highlight the importance of ecosystem adaptation and reaction of plant functional types to N deposition, when predicting the future C balance of N-polluted cool temperate bogs.

scholarly journals Machine Learning, Ethics, and Change Management: A Data-Driven Approach to Improving Hospital Observation Unit Operations

2021 ◽  
Author(s):  
Dessislava Pachamanova ◽  
Vera Tilson ◽  
Keely Dwyer-Matzky
Keyword(s):  
Machine Learning ◽  
Change Management ◽  
Process Improvement ◽  
Operations Management ◽  
Model Performance ◽  
Machine Learning Algorithms ◽  
Business Analytics ◽  
Observation Unit ◽  
Improvement Project ◽  
Data Driven Approach

This case discusses a process improvement project aimed at maximizing the use of hospital capacity as the flu season looms. Dr. Erin Kelly heads the observation unit and turns to predictive models to improve the assignment of patients to her unit. The case covers three major themes: (1) data analytics life cycle and interface of predictive and prescriptive analytics in the context of process improvement, (2) design and ethical application of machine learning models, and (3) effecting organizational change to operationalize the findings of the analysis. Realistic data, R code, and Excel models are provided. The rich context of the case allows for discussing change management in a healthcare organization, analytics problem framing and model mapping, service process capacity analysis and Little’s law, data summaries and visualizations, interpretable machine learning algorithms, evaluations of predictive model performance, algorithmic bias, and dealing with dirty data. The case is appropriate for use in courses in machine learning, business analytics, operations management, and operations research, both at the advanced undergraduate level and at the master’s/MBA level.

scholarly journals Seasonal variations in carbon dioxide exchange in an alpine wetland meadow on the Qinghai-Tibetan Plateau

2010 ◽  
Vol 7 (4) ◽  
pp. 1207-1221 ◽  
Author(s):  
L. Zhao ◽  
J. Li ◽  
S. Xu ◽  
H. Zhou ◽  
Y. Li ◽  
...  
Keyword(s):  
Carbon Dioxide ◽  
Tibetan Plateau ◽  
Carbon Sink ◽  
Ecosystem Respiration ◽  
Gross Primary Production ◽  
Carbon Dioxide Exchange ◽  
Research Station ◽  
Rain Event ◽  
Area Index ◽  
Alpine Wetland

Abstract. Alpine wetland meadow could functions as a carbon sink due to it high soil organic content and low decomposition. However, the magnitude and dynamics of carbon stock in alpine wetland ecosystems are not well quantified. Therefore, understanding how environmental variables affect the processes that regulate carbon fluxes in alpine wetland meadow on the Qinghai-Tibetan Plateau is critical. To address this issue, Gross Primary Production (GPP), Ecosystem Respiration (Reco), and Net Ecosystem Exchange (NEE) were examined in an alpine wetland meadow using the eddy covariance method from October 2003 to December 2006 at the Haibei Research Station of the Chinese Academy of Sciences. Seasonal patterns of GPP and Reco were closely associated with leaf area index (LAI). The Reco showed a positive exponential to soil temperature and relatively low Reco occurred during the non-growing season after a rain event. This result is inconsistent with the result observed in alpine shrubland meadow. In total, annual GPP were estimated at 575.7, 682.9, and 630.97 g C m−2 in 2004, 2005, and 2006, respectively. Meanwhile, the Reco were equal to 676.8, 726.4, 808.2 g C m−2, and thus the NEE were 101.1, 44.0 and 173.2 g C m−2. These results indicated that the alpine wetland meadow was a moderately source of carbon dioxide (CO2). The observed carbon dioxide fluxes in the alpine wetland meadow were higher than other alpine meadow such as Kobresia humilis meadow and shrubland meadow.

scholarly journals Effects of a windthrow disturbance on the carbon balance of a broadleaf deciduous forest in Hokkaido, Japan

2015 ◽  
Vol 12 (23) ◽  
pp. 6837-6851 ◽  
Author(s):  
K. Yamanoi ◽  
Y. Mizoguchi ◽  
H. Utsugi
Keyword(s):  
Forest Management ◽  
Carbon Balance ◽  
Deciduous Forest ◽  
Carbon Sink ◽  
Ecosystem Respiration ◽  
Gross Primary Production ◽  
Co2 Flux ◽  
White Birch ◽  
Eddy Covariance Method ◽  
Area Index

Abstract. Forests play an important role in the terrestrial carbon balance, with most being in a carbon sequestration stage. The net carbon releases that occur result from forest disturbance, and windthrow is a typical disturbance event affecting the forest carbon balance in eastern Asia. The CO2 flux has been measured using the eddy covariance method in a deciduous broadleaf forest (Japanese white birch, Japanese oak, and castor aralia) in Hokkaido, where incidental damage by the strong Typhoon Songda in 2004 occurred. We also used the biometrical method to demonstrate the CO2 flux within the forest in detail. Damaged trees amounted to 40 % of all trees, and they remained on site where they were not extracted by forest management. Gross primary production (GPP), ecosystem respiration (Re), and net ecosystem production were 1350, 975, and 375 g C m−2 yr−1 before the disturbance and 1262, 1359, and −97 g C m−2 yr−1 2 years after the disturbance, respectively. Before the disturbance, the forest was an evident carbon sink, and it subsequently transformed into a net carbon source. Because of increased light intensity at the forest floor, the leaf area index and biomass of the undergrowth (Sasa kurilensis and S. senanensis) increased by factors of 2.4 and 1.7, respectively, in 3 years subsequent to the disturbance. The photosynthesis of Sasa increased rapidly and contributed to the total GPP after the disturbance. The annual GPP only decreased by 6 % just after the disturbance. On the other hand, the annual Re increased by 39 % mainly because of the decomposition of residual coarse-wood debris. The carbon balance after the disturbance was controlled by the new growth and the decomposition of residues. The forest management, which resulted in the dead trees remaining at the study site, strongly affected the carbon balance over the years. When comparing the carbon uptake efficiency at the study site with that at others, including those with various kinds of disturbances, we emphasized the importance of forest management as well as disturbance type in the carbon balance.

Sign in / Sign up

Export Citation Format

Share Document