Use of remote sensing to characterize the phenological development and to predict sweet potato yield in two growing seasons

Tedesco, Danilo; Oliveira, Maílson Freire de; Santos, Adão Felipe dos; Silva, Edgard Henrique Costa; Rolim, Glauco de Souza; Silva, Rouverson Pereira da

doi:10.1016/j.eja.2021.126337

“…(Suresh et al, 2021), and grapevine (Vitis vinifera L.) (Charalampopoulos et al, 2021). Few works used the concept of degree days associated with spectral remote sensing data to model crop grain yield with machine-learning techniques (Tedesco, Moreira, et al, 2021;Tedesco, Oliveira, et al, 2021); until the moment of this study, none were found with corn cultivation.…”

Section: Core Ideasmentioning

confidence: 99%

Corn grain yield forecasting by satellite remote sensing and machine‐learning models

Pinto

¹

,

Zerbato

²

,

Rolim

³

et al. 2022

Agronomy Journal

3

0

View full text Add to dashboard Cite

This study aimed to evaluate the performance of six machine-learning models in forecasting corn (Zea mays L.) grain yield before harvest using, as input, variables in the models, some of the most-used vegetation indices (VIs) and spectral bands in the literature, as well as using data at 770 and 980 sum of degree days (SDD).The field study was carried out in a commercial area in the 2017-2018 and 2018-2019 harvests. Spectral data were obtained from Sentinel-2 satellite images and were used as input variables in the proposed models: artificial neural networks (ANN), k-nearest neighbors (KNN), random forest (RF), and support vector machine (SVM). The maximum R 2 and minimum values of mean absolute error (MAE) and RMSE were 0.89, 0.33, and 0.42 t ha −1 , respectively, for the RF algorithm using all input variables. The results obtained in the present study show that it is possible to predict corn grain yield 80 d before harvest using only VIs for the crop. Testing the various combinations of spectral bands and VIs resulted in obtaining the GREEN band and the VI global environment monitoring index (GEMI) as the best predictor variables in the present study. The use of more than one SDD did not improve the performance of the models tested. The models developed using data at 980 SDD obtained the best precision and accuracy performance both in the scenario with all model input variables and with the two best predictors. The KNN algorithm obtained the best performance in the precision and accuracy metrics for most of the scenarios studied in the present work.

show abstract

“…Daily CO 2 measurements can be made using the Eddy Covariance technique [17,18,19], although this has the disadvantage of being a point (local) study. In this sense using orbital data modeling to estimate the daily variation of several aspects (e.g, climate, meteorological, land-use changes, ecosystems services) for an entire region has become common [16,20,21,22,23].…”

Section: Introductionmentioning

confidence: 99%

Daily Model of Xco2 Based on Orbital Observations for the State of São Paulo – Brazil

Costa

¹

,

Santos

²

,

Panosso

³

et al. 2022

Preprint

0

View full text Add to dashboard Cite

Background: Understanding the behavior of carbon dioxide (CO2) it is crucial to create strategies to deal with climate change. Several space missions were designed to monitor this and other greenhouse gases and studies at global and large regional scales were developed using these remote sensing tools. However, there is still a time gap in orbital data, since the revisit time of a satellite at the same location for this type of observation is not daily. Daily measurements of CO2 can be made using Eddy Covariance technique, although this type of study is at a very local scale. In this study, we aimed to build a daily model to estimate the natural CO2 in the atmosphere.Results: The data was retrieved from the Orbiting Carbon Observatory-2 (OCO-2), NASA-POWER and, Application for Extracting and Exploring Analysis Ready Samples (AppEEARS) and consist in a time-series from 2015 to 2019. To summarize the most relevant factor we used the Variance Inflation Factor (VIF) after we performed the Pearson’s Correlation and apply descriptive statistics in the significant variables (p < 0.05). The model was construed using the stepwise regression method and the selected model was defined by the lowest RMSE in training (~0.6 ppm). The most related variables with Xco2 were Global Radiation (Qg), Sun Induced Chlorophyll Fluorescence (SIF) and, Relative Humidity (RH), all these factors were negatively correlated with the CO2 concentration. The model has the best perform with the Qg and RH (RMSE = 0.47 ppm, R2 = 0.44, p < 0.01).Conclusion: In summary, the cycle of atmospheric CO2 in the state of São Paulo has higher average values during April to October, and the lowest averages of Xco2 were usually observed between December to March and the inverse behavior was observed for SIF 757, Global Radiation (Qg) and Relative Humidity (RH). Concerning the daily model, despite the differences between the spatial observations, the model derived here was capable to estimate the cycle of atmospheric CO2 using only meteorological data.

show abstract

“…In this sense using orbital data, such as Orbiting Carbon Observatory-2 (OCO-2), has become more common [ 1 , 2 ]. Remote sensing data also can be used to estimate the daily variations of different aspects (e.g., climate, meteorological, land-use changes, ecosystems services) for a larger area [ 16 , 20 – 23 ].…”

Section: Introductionmentioning

confidence: 99%

An empirical model for estimating daily atmospheric column-averaged CO2 concentration above São Paulo state, Brazil

Costa

¹

,

Santos

²

,

Panosso

³

et al. 2022

Carbon Balance Manage

5

0

View full text Add to dashboard Cite

Background The recent studies of the variations in the atmospheric column-averaged CO2 concentration ($${\text{X}}_{{{\text{CO}}_{{2}} }}$$ X CO 2 ) above croplands and forests show a negative correlation between $${\text{X}}_{{{\text{CO}}_{{2}} }}$$ X CO 2 and Sun Induced Chlorophyll Fluorescence (SIF) and confirmed that photosynthesis is the main regulator of the terrestrial uptake for atmospheric CO2. The remote sensing techniques in this context are very important to observe this relation, however, there is still a time gap in orbital data, since the observation is not daily. Here we analyzed the effects of several variables related to the photosynthetic capacity of vegetation on $${\text{X}}_{{{\text{CO}}_{{2}} }}$$ X CO 2 above São Paulo state during the period from 2015 to 2019 and propose a daily model to estimate the natural changes in atmospheric CO2. Results The data retrieved from the Orbiting Carbon Observatory-2 (OCO-2), NASA-POWER and Application for Extracting and Exploring Analysis Ready Samples (AppEEARS) show that Global Radiation (Qg), Sun Induced Chlorophyll Fluorescence (SIF) and, Relative Humidity (RH) are the most significant factors for predicting the annual $${\text{X}}_{{{\text{CO}}_{{2}} }}$$ X CO 2 cycle. The daily model of $${\text{X}}_{{{\text{CO}}_{{2}} }}$$ X CO 2 estimated from Qg and RH predicts daily $${\text{X}}_{{{\text{CO}}_{{2}} }}$$ X CO 2 with root mean squared error of 0.47 ppm (the coefficient of determination is equal to 0.44, p < 0.01). Conclusion The obtained results imply that a significant part of daily $${\text{X}}_{{{\text{CO}}_{{2}} }}$$ X CO 2 variations could be explained by meteorological factors and that further research should be done to quantify the effects of the atmospheric transport and anthropogenic emissions.

show abstract

Use of remote sensing to characterize the phenological development and to predict sweet potato yield in two growing seasons

Cited by 21 publications

References 53 publications

Corn grain yield forecasting by satellite remote sensing and machine‐learning models

Corn grain yield forecasting by satellite remote sensing and machine‐learning models

Daily Model of Xco2 Based on Orbital Observations for the State of São Paulo – Brazil

An empirical model for estimating daily atmospheric column-averaged CO2 concentration above São Paulo state, Brazil

Contact Info

Product

Resources

About