Search results for "Empirical model"

Crop specific algorithms trained over ground measurements provide the best performance for GAI and fAPAR estimates from Landsat-8 observations

2021

Abstract Estimation of Green Area Index (GAI) and fraction of Absorbed Photosynthetically Active Radiation (fAPAR) from decametric satellites was investigated in this study using a large database of ground measurements over croplands. It covers six main crop types including rice, corn, wheat and barley, sunflower, soybean and other types of crops. Ground measurements were completed using either digital hemispherical cameras, LAI-2000 or AccuPAR devices over sites representative of a decametric pixel. Sites were spread over the globe and the data collected at several growth stages concurrently to the acquisition of Landsat-8 images. Several machine learning techniques were investigated to re…

2016

Gianluca Tramontana was supported by the GEOCARBON EU FP7 project (GA 283080). Dario Papale, Martin Jung and Markus Reichstein acknowledge funding from the EU FP7 project GEOCARBON (grant agreement no. 283080) and the EU H2020 BACI project (grant agreement no. 640176). Gustau Camps-Valls wants to acknowledge the support by an ERC Consolidator Grant with grant agreement 647423 (SEDAL). Kazuhito Ichii was supported by Environment Research and Technology Development Funds (2-1401) from the Ministry of the Environment of Japan and the JAXA Global Change Observation Mission (GCOM) project (no. 115). Christopher R. Schwalm was supported by National Aeronautics and Space Administration (NASA) gran…

Trade-offs between ecosystem service provision and the predisposition to disturbances: a NFI-based scenario analysis

2020

Abstract Background Scenario analyses that evaluate management effects on the long-term provision and sustainability of forest ecosystem services and biodiversity (ESB) also need to account for disturbances. The objectives of this study were to reveal potential trade-offs and synergies between ESB provision and disturbance predisposition at the scale of a whole country. Methods The empirical scenario model MASSIMO was used to simulate forest development and management from years 2016 to 2106 on 5086 sample plots of the Swiss National Forest Inventory (NFI). We included a business-as-usual (BAU) scenario and four scenarios of increased timber harvesting. Model output was evaluated with indic…

Modelling and prediction of retention in high-performance liquid chromatography by using neural networks

1995

Multi-layer feed-forward neural networks trained with an error back-propagation algorithm have been used to model retention behaviour of liquid chromatography as a function of the composition of the mobile phases. Conventional hydro-organic and micellar mobile phases were considered. Accurate retention modelling and prediction have been achieved using mobile phases defined by two, three and four parameters. With micellar mobile phases, the parameters involved included the concentrations of surfactant and organic modifier, pH and temperature. It is shown that neural networks provide a competitive tool to model varied inherent nonlinear relationships of retention behaviour with respect to the…

Incorporation of aerosol effects in a clear-sky semi-empirical model of UVER radiation for Valencia, Spain

2011

The study develops a simple but physically based model for estimating erythemal irradiance [(UV erythemal radiation (UVER)] for cloudless urban regions with substantial aerosol load, such as that of the Valencia environment in Spain. The model estimates direct and diffuse UVER for cloudless aerosol-free conditions using the LibRadtran model with a DISORT algorithm. Aerosol optical thickness for UVER (τaER) is obtained as a residual term by comparing measured direct UVER against modelled direct UVER in the absence of aerosol load. On average, τaER is 18% higher than τ data extrapolated to 305 nm using the CIMEL CE-318. Comparison of measured direct and diffuse UVER with model estimates provi…

Modelling of thermo-chemical properties over the sub-solidus MgO–FeO binary, as a function of iron spin configuration, composition and temperature

2014

Thermo-chemical properties and T–X phase relations diagram of the (Mg,Fe)O solid solution are modelled using mixing Helmholtz energy, ΔF(T,x)mixing, calculated by quantum mechanical and semi-empirical techniques. The sub-solidus MgO–FeO binary has been explored as a function of composition, with iron either in high-spin (HS) or low-spin (LS) configuration. Only the HS model provides physically sound results at room pressure, yielding a correct trend of cell edge versus composition, whereas LS’s issues are at variance with observations. Mixing Helmholtz energy has been parametrized by the following relationship: ΔF(T,x)mixing = x × y × [U0(T) + U1(T) × (x – y) + U2(T) × (x − y)2]−T × S(x,y)c…

Modelo empírico para la determinación de clorofila-a en aguas continentales a partir de los futuros Sentinel-2 y 3. Validación con imágenes HICO

2014

[EN] Chlorophyll-a concentration is one of the main indicators of inland waters quality. Using CHRIS/PROBA images and in situ data obtained in four lakes in Colombia and Spain, we obtained empirical models for the estimation of chlorophyll-a concentration, which can be directly applied to future images of MSI Sentinel-2 and OLCI Sentinel-3 sensors. The models, based on spectral band indices, were validated with data from the hyperspectral sensor HICO, onboard of the International Space Station.

Using an Adaptive Network-based Fuzzy Inference System to Estimate the Vertical Force in Single Point Incremental Forming

2019

Manufacturing processes are usually complex ones, involving a significant number of parameters. Unconventional manufacturing processes, such as incremental forming is even more complex, and the establishment of some analytical relationships between parameters is difficult, largely due to the nonlinearities in the process. To overcome this drawback, artificial intelligence techniques were used to build empirical models from experimental data sets acquired from the manufacturing processes. The approach proposed in this work used an adaptive network-based fuzzy inference system to extract the value of technological force on Z-axis, which appears during incremental forming, considering a set of…

A semi-empirical multipurpose steady-state model of a fuel cell for household appliances

2013

In this paper, a multipurpose model of a proton exchange membrane fuel cell for household appliances is proposed. According to a conventional mathematical approach, the proposed model is derived from the physical and electro-chemical equations that rule the fuel cell behaviour. Differently from existing models, a parametric analysis is carried out and a few tunable parameters are accurately selected and identified. Furthermore, this paper proposes an innovative technique of unique model architecture which enables the designer to solve by himself the trade-off between complexity and accuracy on the basis of the specific applications. Three different choices could be performed by the designer…

Estimating crop primary productivity with Sentinel-2 and Landsat 8 using machine learning methods trained with radiative transfer simulations

2019

Abstract Satellite remote sensing has been widely used in the last decades for agricultural applications, both for assessing vegetation condition and for subsequent yield prediction. Existing remote sensing-based methods to estimate gross primary productivity (GPP), which is an important variable to indicate crop photosynthetic function and stress, typically rely on empirical or semi-empirical approaches, which tend to over-simplify photosynthetic mechanisms. In this work, we take advantage of all parallel developments in mechanistic photosynthesis modeling and satellite data availability for an advanced monitoring of crop productivity. In particular, we combine process-based modeling with …