We have analyzed the dependence of the Angstrom turbidity parameters on wavelength throughout the visible range by three different methods. We have obtained significant results about the ability of these parameters to represent the turbidity of the atmosphere. An important variation of these coefficients with the wavelength is shown, depending on the method used and the spectral resolution of the data. The log-log plot of aerosol optical thickness vs wavelength appears as an adequate method of obtaining the Angstrom parameters to represent the turbidity of the atmosphere and to model the effect of aerosols on solar radiation.
Traditional potato growth models evidence certain limitations, such as the cost of obtaining the input data required to run the models, the lack of spatial information in some instances, or the actual quality of input data. In order to address these issues, we develop a model to predict potato yield using satellite remote sensing. In an effort to offer a good predictive model that improves the state of the art on potato precision agriculture, we use images from the twin Sentinel 2 satellites (European Space Agency-Copernicus Programme) over three growing seasons, applying different machine learning models. First, we fitted nine machine learning algorithms with various pre-processing scenarios using variables from July, August and September based on the red, red-edge and infra-red bands of the spectrum. Second, we selected the best performing models and evaluated them against independent test data. Finally, we repeated the previous two steps using only variables corresponding to July and August. Our results showed that the feature selection step proved vital during data pre-processing in order to reduce multicollinearity among predictors. The Regression Quantile Lasso model (11.67% Root Mean Square Error, RMSE; R 2 = 0.88 and 9.18% Mean Absolute Error, MAE) and Leap Backwards model (10.94% RMSE, R 2 = 0.89 and 8.95% MAE) performed better when predictors with a correlation coefficient > 0.5 were removed from the dataset. In contrast, the Support Vector Machine Radial (svmRadial) performed better with no feature selection method (11.7% RMSE, R 2 = 0.93 and 8.64% MAE). In addition, we used a random forest model to predict potato yields in Castilla y León (Spain) 1-2 months prior to harvest, and obtained satisfactory results (11.16% RMSE, R 2 = 0.89 and 8.71% MAE). These results demonstrate the suitability of our models to predict potato yields in the region studied.The use of new technologies, such as satellite data, Geographic Information Systems (GIS) or Global Positioning Systems (GPS), can improve crop yield production and its quality [1], helping to secure food supply for the future as well as reducing the negative impacts resulting from agricultural practices [11]. More specifically, satellite remote sensing data has many applications in agriculture: soil property detection [12], crop type classification [13], crop yield forecast [14], crop health monitoring [15], soil moisture retrieval [16] or weather data assessment [17]. Remote sensing offers vast amounts of information which can be considered big data [18], and can help to improve crop modelling and decision-making. Big data has been described by Wolfert et al. [19] as "massive volumes of data with a wide variety that can be captured, analysed and used for decision-making", with said authors expecting big data to have a major impact on the agricultural sector. In order to improve the use of this data, given its size and variety, machine learning has emerged as an appropriate tool to identify rules and patterns in datasets [20], in addition to autonomously...
[1] Detection and parameterization of forest fires is a task traditionally performed by polar-orbiting sensors, mainly advanced very high resolution radiometer (AVHRR) advanced along track scanning radiometer (AATSR), bispectral infrared detection (BIRD), and Moderate Resolution Imaging Spectroradiometer (MODIS). However, their time resolution is a problem to operate in real time. New geostationary sensors have proven their capacity for Earth observation. GOES, MSG, and MTSAT are already operative with time resolutions below 30 min. The international community feels that a real-time global observation network may become a reality, which is the aim of the Global Observations of Forest Cover and Land Cover Dynamics (GOFC/GOLD) FIRE Mapping and Monitoring program, focusing internationally on decision-making concerning research into global change. This paper shows the operation in real time by the MSG SEVIRI sensor over the Iberian Peninsula. For fire detection, a temporal gradient of temperature 3.9 mm is used, which is more efficient at eliminating incoming false alarms from solar reflection. Capacity to detect hot forest fires below 0.3 ha in Mediterranean latitudes has been analyzed along with the conditions in which it is possible to apply the MODIS methodology to establish the fire radiative energy (FRE) by means of experimental relation. We found that in this case, fire size can introduce maximum differences of 40% in FRE for small-scale fires. The capacity of this sensor is shown in different cases that have greatly impacted Spain and Portugal because of the loss of human life.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.