# Modeling Actual Evapotranspiration with MSI-Sentinel Images and Machine Learning Algorithms

^{1}

^{2}

^{3}

^{4}

^{5}

^{*}

## Abstract

**:**

_{r}F (Evapotranspiration Fraction) of sugar can crop using the METRIC (Mapping Evapotranspiration at High Resolution with Internalized Calibration) model with data from the Sentinel-2 satellites constellation. In order to achieve this goal, images from the MSI sensor (MultiSpectral Instrument) from the Sentinel-2 and the OLI (Operational Land Imager) and TIRS (Thermal Infrared Sensor) sensors from the Landsat-8 were acquired nearly at the same time between the years 2018 and 2020 for sugar cane crops. Images from OLI and TIR sensors were intended to calculate ET

_{r}F through METRIC (target variable), while for the MSI sensor images, the explanatory variables were extracted in two approaches, using 10 m (approach 1) and 20 m (approach 2) spatial resolution. The results showed that the algorithms were able to identify patterns in the MSI sensor data to predict the ET

_{r}F of the METRIC model. For approach 1, the best predictions were XgbLinear (R

^{2}= 0.80; RMSE = 0.15) and XgbTree (R

^{2}= 0.80; RMSE = 0.15). For approach 2, the algorithm that demonstrated superiority was the XgbLinear (R

^{2}= 0.91; RMSE = 0.10), respectively. Thus, it became evident that machine learning algorithms, when applied to the MSI sensor, were able to estimate the ET

_{r}F in a simpler way than the one that involves energy balance with the thermal band used in the METRIC model.

## 1. Introduction

_{r}F) through the instantaneous evapotranspiration (ET

_{ints}) and the reference potential evapotranspiration of the alfalfa (ET

_{r}) or grass (ET

_{o}) on a daily scale. This model is very complex, as it demands, a priori, the estimation of parameters for the energy balance calculations, which can be prone to errors since this model presents an interactive method of selecting “hot” and “cold” pixels to calculate aerodynamic resistance to heat transport and exchange derived from the SEBAL model [6].

_{a}) using the MSI sensor will be of great value for the scientific community and field professionals, enabling determining ET

_{a}with a better spatial and temporal resolution during crop cycles, and can even be integrated with sensors on other satellite platforms forming a multi-sensor suite, which, in the absence of information from one sensor, allows it to be complemented by the other, in concordance with the approach described by Filgueiras et al. [9]. Another important aspect is that, even though the MSI does not include the thermal infrared band, ET

_{a}can be estimated without the surface temperature information, which can reduce the introduction of additional errors as models involving thermal information have, in their structure, the complex energy balance to quantify the latent energy of the system. Furthermore, thermal bands have a coarser spatial resolution, so interpolation is often necessary to align pixel sizes with those of the other bands, such as Landsat 5.7 and 8. Alternatively, modeling evapotranspiration in the absence of data from the thermal band can generate unsatisfactory results due to the intrinsic relationship between vegetation canopy temperature derived from the thermal band with stomatal conductance [10,11].

_{r}F) used in the METRIC model from the data of the Sentinel-2 satellites constellation that does not use thermal data on the sugar cane crop used in this case study.

## 2. Materials and Methods

#### 2.1. Study Area

#### 2.2. Landsat-8 and Sentinel-2 Data

_{r}F) using the METRIC model, this being the response variable, whereas data from the MSI sensor were used as predictor variables in the machine learning models. The spectral and spatial characteristics of the sensors used are available in Table 1 and Table 2.

_{c}) and actual evapotranspiration (ET

_{a}) during the sugar cane cycle. The estimation was performed by both the METRIC model and the suggested model.

#### 2.3. Response Variable

_{r}F), was obtained for each pixel, with a 30 m × 30 m spatial resolution, from the METRIC model. ET

_{r}F is reckoned by dividing instantaneous evapotranspiration (ET

_{inst}) in each pixel by the hourly reference evapotranspiration (ET

_{r}) given by the meteorological station. Allen [7] standardized ET

_{r}for alfalfa at 0.5 m high. According to the authors, when using this condition, the ET

_{r}F can be considered equivalent to the crop coefficient (K

_{c}). It also enables the extrapolation of the crop’s actual evapotranspiration when the satellite switches to the daily 24 h level. Thus, the ET

_{r}F is determined by Equation (1).

_{inst}is the instantaneous evapotranspiration (mm·h

^{−1}) and ET

_{r}is the reference evapotranspiration (mm·h

^{−1}) standardized to alfalfa at 0.5 m height at the moment the satellite is passing.

_{inst}is calculated from the latent energy consumed in the evapotranspiration (ET) process and the latent heat of vaporization Equation (2).

^{−2}); ρ

_{w}is the density of water (~1000 kg m

^{−3}); λ is the latent heat of vaporization (J kg

^{−1}).

_{s}is the surface temperature (°K) determined by band 10 of the TIRS sensor (Table 1).

_{n}), a sensible flux of heat transferred to the ground (G), and a sensible flux of heat convected to air (H). These three components, responsible for determining LE, are usually expressed in W m

^{−2}.

_{n}is the radiant energy of the surface that is partitioned into H, G, and LE and is determined by Equation (5).

_{s↓}is the input of shortwave radiation (W m

^{−2}); α is the surface albedo (adim.) determined by bands 2, 3, 4, 5, 6, and 7 of the Landsat-8 (Table 1); R

_{L↓}and R

_{L↑}are the input and output of long waves (W m

^{−2}), respectively; and ԑ

_{0}is the surface thermal emissivity.

^{2}m

^{−2}) estimated by the methodology applied by Allen [2].

_{air}is the air density (kg m

^{−3}); C

_{p}is the specific heat of air at constant pressure (J kg

^{−1}K

^{−1}); dT is the temperature difference between two heights (z1 and z2) in an area close to the surface; r_ah is the aerodynamic drag (s m

^{−1}) between these two heights.

#### 2.4. Data Extraction for Training

_{r}F values lower than 0 that eventually contained some pixels generated by noise in some images were filtered out. In the end, data frame files with geographic coordinates, spectral bands, and ET

_{r}F were obtained.

#### 2.5. Training and Statistical Evaluation of Models

#### 2.5.1. Production and Selection of Predictor Variables

_{x}and ρ

_{y}correspond to the surface reflectance of the wavelengths of the MSI sensor.

#### 2.5.2. Training and Test

^{2}), Equation (9); root mean squared error (RMSE), Equation (10); mean absolute error (MAE), Equation (11); mean bias error (MBE), Equation (12).

#### 2.5.3. Residual Analysis

_{r}F (approaches 1 and 2) and the observed ET

_{r}F (METRIC) were extracted from the 11 pivots (Figure 1) to reckon the residues (Equation (13)).

#### 2.6. Application

_{c}) and the actual evapotranspiration (ET

_{a}) during the sugarcane crop cycle for the best METRIC model. In addition to K

_{c}, water consumption during the sugar cane crop cycle also was estimated using 29 images of the MSI sensor from 11/23/2019 (DAE-days after emergency 05) to 09/03/2020 (DAE 290) and 17 images of the OLI and TRIS sensor between 12/07/2019 (DAE 19) and 09/04/2020 (DAE 291).

_{r}F. According to Allen [7], the ET

_{r}F is equivalent to the K

_{c}when using the ET

_{r}of the alfalfa, which is the condition in which the ET

_{r}F was modeled. The 17 images of the OLI and TIRS sensor were used to calculate K

_{c}through the METRIC model. After quantifying the K

_{c}, the crop’s actual evapotranspiration was established. Therefore, the accumulated reference evapotranspiration for a 24 h (ET

_{r-24}) period was calculated on the same day the image was acquired.

_{r-24}in each day was calculated using the Penman–Monteith equation standardized by the ASCE (American Society of Civil Engineers) [32], and meteorological data were acquired in the A539 station, Mocambinho from the INMET (National Institute of Meteorology). With all the ET

_{r-24}and K

_{c}, the ET

_{a}in each pixel was established by Equation (14).

_{a}of each date. Thus, the area under the curve, which corresponds to the total evapotranspiration during the cycle, was calculated. This process was performed using function auc from the MESS package [33] for the R language.

## 3. Results

#### 3.1. Models

^{2}= 0.80 and RMSE = 0.15; followed by the Cubist with R

^{2}= 0.77 and RMSE = 0.15; lastly, and with the worst result, the multiple linear regression (Lm) with the minimum R

^{2}= 0.73 and the major RMSE = 0.17. Regardless of the model, the high dispersion shown on the test draws attention, especially in values lower than 0.6 (Figure 6). Ke et al. [34], when estimating evapotranspiration using machine learning in Landsat-8 data and MODIS for a heterogeneous environment, noted that in areas with crops, there was a higher dispersion between predicted vs. observed values than in areas with forest, grazing, and bushes. Thus, results from these authors agree with the ones found here, as, in crop areas, there is a higher surface movement, being more dynamic both in terms of vegetation cover and in terms of soil moisture.

^{2}. R

^{2}, as in approach 1, had different values among these last three models, being 0.91 for XgbLinear and 0.90 for Cubist and XgbTree. When comparing Figure 6 and Figure 7, approach 2 obtained more satisfying results than approach 1, with models with R

^{2}higher than 0.88 and RMSE lower than 0.11, whereas approach 1 had R

^{2}lower than 0.80 and RMSE higher than 0.15. It seems that approach 2 even reduced the dispersion seen in Figure 6 significantly.

#### 3.2. Residual Analysis

_{r}F is low, especially for values under 0.6, as previously discussed; this is better shown in Figure 9.

_{r}F values through METRIC and machine learning models. However, for that pivot, this result was more prominent when using Sentinel-2 images, as they showed greater spatial resolution. Additionally, the thermal band on Landsat-8, which has a coarser resolution (100 m), can mask nuances of the surface of the monitored area.

#### 3.3. Models Application

_{c}) during the sugar cane cycle, determined through the XgbLinear, which presented better metrics for approaches 1 and 2 through the METRIC model and also through the FAO-56 report [1].

_{c}for approaches 1 and 2 were 0.3 and 0.32, respectively, while METRIC estimated a K

_{c}of 0.20, and the K

_{c}determined by the 56 FAO’s report [1] is 0.40. In phase II (development), the K

_{c}curves in approaches 1 and 2 become closer to the ones of the METRIC as the phenological state progresses, as well as the K

_{c}-FAO curve becomes closer to both approaches and distances a little from the METRIC curve. For phase III (mid-season) crop growth, the average Kc was 0.98 for approach 1 and 1.00 for METRIC, while for approach 2, it was 1.02, and FAO’s 56 report recommends using a 1.25 value. Moreover, in phase III, the METRIC curve behaves similarly to approach 2, which corroborates the results found in the models’ tests. In phase IV (late-season), maturation, approach 1 was the most distant from both FAO’s and METRIC’s K

_{c}, with a value equal to 0.69, while approach 2 had a K

_{c}of 0.76 and METRIC of 0.77. Dingre and Gorantiwar [35], when quantifying K

_{c}for sugar cane through the water balance method, found medium values for phases I, III, and IV of 0.36, 1.20, and 0.78, respectively. Silva et al. [36], for the Brazilian semiarid region, obtained a K

_{c}for ratoon cane in phases I, III, and IV equal to 0.65, 1.10, and 0.85, different from FAO’s recommendation. This evinces a divergence in K

_{c}values shown in the literature from the ones recommended, which can be explained by the specificity of the local weather in which each study was performed, as well as the physiological conditions of the crop at the time of the satellite imaging. Phase III, for this work, reached the maximum value of 1.09; however, it showed variations throughout the whole phase.

_{c}information throughout the crop cycle than Landsat-8, which is important to obtain a major temporal variability of this coefficient. This can lead to more assertive crop management than if only Landsat-8 data were used. Saleem and Awange [37] mention that Sentinel-2 represents a new age for obtaining more precise information about the Earth’s surface, as it has a greater spatial and temporal resolution among satellites that provide images for free. Nevertheless, information referring to K

_{c}can be expanded when joining the two orbital platforms, as more information will be obtained with a larger frequency of images, as highlighted in Filgueiras et al. [9].

_{a}larger than for the rest of the pivot. On that day, crops were in the initial emergency phase, and soil was exposed in most of the area, receiving water from irrigation. This ray corresponds to the moisture in the exposed soil, and it is displaced clockwise from the irrigation equipment. Such information is only visible with 10 and 20 m resolution, and thus, the METRIC model, due to the use of thermal images, can not show. Spatially detailed information, as seen in the Sentinel-2 images of Figure 11, has great value for field professionals. Coinciding dates between Sentinel-2 and Landsat-8 show high similarities in the spatial ET

_{a}between approaches 1 and 2 with METRIC. Approach 2 stands out for having larger spatial proximity. Such proximity is evidenced in Table 5, in which the averages ET

_{as}in approach 2 have the smallest differences in the estimated averages by the METRIC model. In addition, the standard deviation for approach 2 was also smaller than approach 1 but larger than the METRIC model. This fact might be attached to the more detailed spatial resolutions of approaches 1 and 2 when compared to the method using the METRIC model.

_{a}, it was found that the sugar cane total water demand along the crop cycle was 1417.77 mm for approach 1, 1474.26 mm for approach 2, and 1544.11 mm for METRIC. It is perceptible that total evapotranspiration estimated for approaches 1 and 2 were close to the total evapotranspiration by METRIC, where percentual differences were 8.18 for approach 1 and 4.52 for approach 2 when compared to METRIC. Approach 2 had a closer value to the one estimated by METRIC, going against the values found for dates indicated in Figure 11. Sugar cane total evapotranspiration during its cycle, found by Dingre and Gorantiwar [35], was 1388 mm. The one found by Silva et al. [38] for the Brazilian Northeast conditions was 1600 mm. Thus, it can be noticed that the total evapotranspiration found in this work is close to the values found in Brazil.

## 4. Discussions

_{r}F values lower than 0.6 in both approaches may be related to greater heterogeneity of the cultivated area. When ET

_{r}F values are lower than 0.6, the crop does not completely cover the soil, and there may be patches of soil with different colors, moisture, etc., a proliferation of weeds in parts of the area, and even a greater degree of the vigor of the crop in parts of the plot. The fact that approach 1 is more dispersed than approach 2 is linked, quantitatively and qualitatively, to their predictors. Approach 2 had a total of 12 predictors: the same as approach 1 and some others, mainly the short infrared wavelength and red edge.

_{r}F to be equal to K

_{c}when using the reference evapotranspiration of alfalfa [7,48,49,50]. However, this interpretation is not correct because sensors on board satellites or other platforms capture the information that is occurring in the field under natural conditions, and one cannot be sure that the plant is in maximum water comfort and with nutritional, pest, disease, and weed management adequate for maximum water uptake. Thus both METRIC and the models trained in this study estimate the product between K

_{c}and K

_{s}(stress coefficient), the latter being responsible for reducing ET

_{r}F to values lower than K

_{c}when the crop is under stress or making it equal to K

_{c}when the plant is in favorable conditions for maximum water uptake.

## 5. Conclusions

^{2}of 0.91 and RMSE of 0.10, whereas the metrics for the same model considering approach 1 were 0.80 and 0.15 for the R

^{2}and RMSE, respectively. This result was mainly influenced by the greater number of spectral bands that are strongly related to water content as the short infrared and the red edge, thus being the model to be applied. However, all models developed showed limitations when the dependent variable presents values lower than 0.6, a condition in which the crop canopy has not completely covered the soil, and there is greater variability.

_{r}F since the analysis had values close to zero and the maximum distance only in the linear regression algorithms for both approach 1 and approach 2. Furthermore, it was possible to note that ET

_{r}F cannot be considered the same as K

_{c}because the onboard sensors capture the actual condition of the crop in the field, hydric comfort or not. Hence, ET

_{r}F can be understood as the product between K

_{c}and K

_{s}that best represents field conditions.

_{r}F through spectral information, complementing the METRIC model estimation using OLI and TIRS sensors and increasing the frequency that information is generated for areas of interest. The combination of these sensors is useful to obtain the highest temporal resolution of the crop, especially for irrigated agriculture, which requires K

_{c}and K

_{s}coefficients to be determined daily for adequate replenishment of the irrigation blade.

## Supplementary Materials

## Author Contributions

## Funding

## Data Availability Statement

## Conflicts of Interest

## Abbreviations

ET_{a} | Actual Evapotranspiration |

ET_{ints} | Instantaneous Evapotranspiration |

ET_{o} | Reference Potential Evapotranspiration of the Grass |

ET_{r} | Reference Potential Evapotranspiration of the Afalfa |

ET_{r}F | Evapotranspiration Fraction |

METRIC | Mapping Evapotranspiration at High Resolution with Internalized Calibration |

ML | Machine Learning |

MSI | MultiSpectral Instrument |

OLI | Operational Land Imager |

R^{2} | Coefficient of Determination |

RMSE | Root Mean Squared Error |

MAE | Mean Absolute Error |

MBE | Mean Bias Error |

SAFER | Simple Algorithm for Evapotranspiration Retrieving |

SEBAL | Surface Energy Balance Algorithm for Land |

TIRS | Thermal Infrared Sensor |

P | Precipitation |

T_{mean} | Mean Air Temperature |

T_{max} | Maximum Air Temperature |

T_{min} | Minimum Air Temperature |

µm | Micrometer |

m | Meter |

K_{c} | Crop Coefficient |

LE | Latent Energy |

ρ_{w} | Density of Water |

λ | Latent Heat of Vaporization |

T_{s} | Surface Temperature |

R_{n} | Net Radiation |

G | Sensible Flux of Heat Transferred to the Ground |

H | Sensible Flux of Heat Convected to Air |

R_{s}_{↓} | Input of Shortwave Radiation |

α | Surface Albedo |

R_{L}_{↓} | Input of Long Waves |

R_{L}_{↑} | Output of Long Waves |

ԑ_{0} | Surface Thermal Emissivity |

LAI | Leaf Area Index |

ρ_{air} | Air Density |

C_{p} | Specific Heat of Air at Constant Pressure |

dT | Temperature Difference Between Two Heights |

r_{ah} | Aerodynamic Drag |

ρB | Reflectance of Blue |

ρG | Reflectance of Green |

ρR | Reflectance of Red |

ρNIR | Reflectance of Near-Infrared |

ρRe | Reflectance of Red Edge |

ρSWIR | Reflectance of Shortwave Infrared |

NRPB | Normalized Ratio Procedure Between Bands |

LM | Linear Regression |

Xgblinear | eXtreme Gradient Boosting-linear method |

XgbTree | eXtreme Gradient Boosting-tree method |

DAE | Days After Emergency |

FAO | Food and Agriculture Organization |

## References

- Allen, R.G.; Pereira, L.S.; Raes, D.; Smith, M. Table of Contents Originated by: Agriculture Crop Evapotranspiration—Guidelines for Computing Crop Water Requirements–FAO Irrigation and Drainage Paper 56, 9th ed.; Food and Agriculture Organization of the United Nations: Rome, Italy, 1998. [Google Scholar]
- Allen, R.; Irmak, A.; Trezza, R.; Hendrickx, J.M.H.; Bastiaanssen, W.; Kjaersgaard, J. Satellite-Based ET Estimation in Agriculture Using SEBAL and METRIC. Hydrol. Process.
**2011**, 25, 4011–4027. [Google Scholar] [CrossRef] - Srivastava, A.; Sahoo, B.; Raghuwanshi, N.S.; Singh, R. Evaluation of Variable-Infiltration Capacity Model and MODIS-Terra Satellite-Derived Grid-Scale Evapotranspiration Estimates in a River Basin with Tropical Monsoon-Type Climatology. J. Irrig. Drain. Eng.
**2017**, 143, 1. [Google Scholar] [CrossRef] - Bastiaanssen, W.G. SEBAL-Based Sensible and Latent Heat Fluxes in the Irrigated Gediz Basin, Turkey. J. Hydrol.
**1999**, 229, 87–100. [Google Scholar] [CrossRef] - Teixeira, A.D.C.; Bastiaanssen, W.; Ahmad, M.-U.; Bos, M. Reviewing SEBAL Input Parameters for Assessing Evapotranspiration and Water Productivity for the Low-Middle São Francisco River Basin, Brazil. Part B: Application to the Regional Scale. Agric. For. Meteorol.
**2009**, 149, 477–490. [Google Scholar] [CrossRef] - Bastiaanssen, W.G.M.; Pelgrum, H.; Wang, J.; Ma, Y.; Moreno, J.F.; Roerink, G.J.; van der Wal, T. A Remote Sensing Surface Energy Balance Algorithm for Land (SEBAL), Part 1: Formulation. J. Hydrol.
**1998**, 212–213, 213–229. [Google Scholar] [CrossRef] - Allen, R.G.; Tasumi, M.; Trezza, R. Satellite-Based Energy Balance for Mapping Evapotranspiration with Internalized Calibration (METRIC)—Applications. J. Irrig. Drain. Eng.
**2007**, 133, 395–406. [Google Scholar] [CrossRef] - Teixeira, A.H.d.C. Determining Regional Actual Evapotranspiration of Irrigated Crops and Natural Vegetation in the São Francisco River Basin (Brazil) Using Remote Sensing and Penman-Monteith Equation. Remote Sens.
**2010**, 2, 1287–1319. [Google Scholar] [CrossRef] - Filgueiras, R.; Mantovani, E.C.; Dias, S.H.B.; Fernandes Filho, E.I.; da Cunha, F.F. Optimizing the Monitoring of Natural Phenomena Through the Coupling of Orbital Multi-Sensors. Geo UERJ.
**2020**, 37, 37832. [Google Scholar] [CrossRef] - Berni, J.A.J.; Zarco-Tejada, P.J.; Sepulcre-Cantó, G.; Fereres, E.; Villalobos, F. Mapping Canopy Conductance and CWSI in Olive Orchards Using High Resolution Thermal Remote Sensing Imagery. Remote Sens. Environ.
**2009**, 113, 2380–2388. [Google Scholar] [CrossRef] - Taiz, L.; Zeiger, E.; Moller, I.M.; Murphy, A. Plant Physiology & Development, 6th ed.; Sinauer Associates Incorporated: Sunderland, MA, USA, 2015; ISBN 9781605353531. [Google Scholar]
- Cervantes, J.; Garcia-Lamont, F.; Rodríguez-Mazahua, L.; Lopez, A. A Comprehensive Survey on Support Vector Machine Classification: Applications, Challenges and Trends. Neurocomputing
**2020**, 408, 189–215. [Google Scholar] [CrossRef] - Adab, H.; Morbidelli, R.; Saltalippi, C.; Moradian, M.; Ghalhari, G.A.F. Machine Learning to Estimate Surface Soil Moisture from Remote Sensing Data. Water
**2020**, 12, 3223. [Google Scholar] [CrossRef] - Filgueiras, R.; Mantovani, E.C.; Dias, S.H.B.; Fernandes Filho, E.I.; da Cunha, F.F.; Neale, C.M.U. New Approach to Determining the Surface Temperature without Thermal Band of Satellites. Eur. J. Agron.
**2019**, 106, 12–22. [Google Scholar] [CrossRef] - Granata, F. Evapotranspiration Evaluation Models Based on Machine Learning Algorithms—A Comparative Study. Agric. Water Manag.
**2019**, 217, 303–315. [Google Scholar] [CrossRef] - Tikhamarine, Y.; Malik, A.; Kumar, A.; Souag-Gamane, D.; Kisi, O. Estimation of Monthly Reference Evapotranspiration Using Novel Hybrid Machine Learning Approaches. Hydrol. Sci. J.
**2019**, 64, 1824–1842. [Google Scholar] [CrossRef] - Virnodkar, S.S.; Pachghare, V.K.; Patil, V.C.; Jha, S.K. Remote Sensing and Machine Learning for Crop Water Stress Determination in Various Crops: A Critical Review. Precis. Agric.
**2020**, 21, 1121–1155. [Google Scholar] [CrossRef] - Carter, C.; Liang, S. Evaluation of Ten Machine Learning Methods for Estimating Terrestrial Evapotranspiration from Remote Sensing. Int. J. Appl. Earth Obs. Geoinf.
**2019**, 78, 86–92. [Google Scholar] [CrossRef] - Xu, T.; Guo, Z.; Xia, Y.; Ferreira, V.G.; Liu, S.; Wang, K.; Yao, Y.; Zhang, X.; Zhao, C. Evaluation of Twelve Evapotranspiration Products from Machine Learning, Remote Sensing and Land Surface Models over Conterminous United States. J. Hydrol.
**2019**, 578, 124105. [Google Scholar] [CrossRef] - Chai, R.; Sun, S.; Chen, H.; Zhou, S. Changes in Reference Evapotranspiration over China during 1960–2012: Attributions and Relationships with Atmospheric Circulation. Hydrol. Process.
**2018**, 32, 3032–3048. [Google Scholar] [CrossRef] - Kadkhodazadeh, M.; Anaraki, M.V.; Morshed-Bozorgdel, A.; Farzin, S. A New Methodology for Reference Evapotranspiration Prediction and Uncertainty Analysis under Climate Change Conditions Based on Machine Learning, Multi Criteria Decision Making and Monte Carlo Methods. Sustainability
**2022**, 14, 2601. [Google Scholar] [CrossRef] - Raza, A.; Shoaib, M.; Faiz, M.A.; Baig, F.; Khan, M.M.; Ullah, M.K.; Zubair, M. Comparative Assessment of Reference Evapotranspiration Estimation Using Conventional Method and Machine Learning Algorithms in Four Climatic Regions. J. Pure Appl. Geophys.
**2020**, 177, 4479–4508. [Google Scholar] [CrossRef] - Tang, D.; Feng, Y.; Gong, D.; Hao, W.; Cui, N. Evaluation of Artificial Intelligence Models for Actual Crop Evapotranspiration Modeling in Mulched and Non-Mulched Maize Croplands. Comput. Electron. Agric.
**2018**, 152, 375–384. [Google Scholar] [CrossRef] - Alvares, C.A.; Stape, J.L.; Sentelhas, P.C.; De Moraes Gonçalves, J.L.; Sparovek, G. Köppen’s Climate Classification Map for Brazil. Meteorol. Zeitschrift
**2013**, 22, 711–728. [Google Scholar] [CrossRef] - Tasumi, M. Progress in Operational Estimation of Regional Evapotranspiration Using Satellite Imagery; University of Idaho: Moscow, ID, USA, 2003. [Google Scholar]
- Olmedo, G.F.; Ortega-Farías, S.; Fonseca-Luengo, D.; de la Fuente-Sáiz, D.; Fuentes-peñailillo, F.; Munafó, M.V. Water: Actual Evapotranspiration with Energy Balance Models. Available online: https://cran.r-project.org/web/packages/water/water.pdf (accessed on 3 January 2021).
- R Core Team. R: A Language and Environment for Statistical Computing, version 3.3.1; R Foundation for Statistical Computing: Vienna, Austria, 2019. [Google Scholar]
- Hijmans, R.J.; van Etten, J.; Cheng, J.; Mattiuzzi, M.; Sumner, M.; Greenberg, J.A.; Lamigueiro, O.P.; Bevan, A.; Racine, E.B.; Shortridge, A.; et al. Raster: Geographic Data Analysis and Modeling. Available online: https://cran.r-project.org/web/packages/raster/index.html (accessed on 10 January 2021).
- Fernandes Filho, E.I. Labgeo: Collection of Functions to Fit Models with Emphasis in Land Use and Soil Mapping. Available online: https://rdrr.io/github/elpidiofilho/labgeo/ (accessed on 8 January 2021).
- Filgueiras, R.; Mantovani, E.C.; Althoff, D.; Fernandes Filho, E.I.; Cunha, F.F. da Crop NDVI Monitoring Based on Sentinel 1. Remote Sens.
**2019**, 11, 1441. [Google Scholar] [CrossRef] - Kuhn, M.; Wing, J.; Weston, S.; Williams, A.; Keefer, C.; Engelhardt, A.; Cooper, T.; Mayer, Z.; Kenkel, B.; Team, R.C. Classification and Regression Training. Available online: https://cran.r-project.org/web/packages/caret/index.html (accessed on 8 January 2021).
- Allen, R.G.; Walter, I.A.; Elliott, R.; Howell, T.; Itenfisu, D.; Jensen, M. The ASCE Standardized Reference Evapotranspiration Equation; American Society of Civil Engineers: Reston, VA, USA, 2005. [Google Scholar]
- Ekstrøm, C.T. MESS: Miscellaneous Esoteric Statistical Scripts. Available online: https://cran.r-project.org/web/packages/MESS/index.html (accessed on 8 January 2021).
- Ke, Y.; Im, J.; Park, S.; Gong, H. Spatiotemporal Downscaling Approaches for Monitoring 8-Day 30 m Actual Evapotranspiration. ISPRS J. Photogramm. Remote Sens.
**2017**, 126, 79–93. [Google Scholar] [CrossRef] - Dingre, S.K.; Gorantiwar, S.D. Determination of the Water Requirement and Crop Coefficient Values of Sugarcane by Field Water Balance Method in Semiarid Region. Agric. Water Manag.
**2020**, 232, 106042. [Google Scholar] [CrossRef] - da Silva, T.G.F.; de Moura, M.S.B.; Zolnier, S.; Soares, J.M.; Vieira, V.J.d.S.; Júnior, W.G.F. Water Requirement and Crop Coefficient of Irrigated Sugarcane in a Semi-Arid Region. Rev. Bras. Eng. Agric. Ambient.
**2012**, 16, 64–71. [Google Scholar] [CrossRef] - Saleem, A.; Awange, J.L. Coastline Shift Analysis in Data Deficient Regions: Exploiting the High Spatio-Temporal Resolution Sentinel-2 Products. CATENA
**2019**, 179, 6–19. [Google Scholar] [CrossRef] - de Silva, V.D.P.; Garcêz, S.L.A.; Silva, B.B.D.; De Albuquerque, M.F.; Almeida, R.S.R. Métodos de Estimativa Da Evapotranspiração Da Cultura Da Cana-de-Açúcar Em Condições de Sequeiro. Rev. Bras. Eng. Agríc. Ambient
**2015**, 19, 411–417. [Google Scholar] [CrossRef] - Li, D.; Li, W.; Zhang, H.; Zhang, X.; Zhuang, J.; Liu, Y.; Hu, C.; Lei, B. Far-Red Carbon Dots as Efficient Light-Harvesting Agents for Enhanced Photosynthesis. ACS Appl. Mater. Interfaces
**2020**, 12, 21009–21019. [Google Scholar] [CrossRef] - Wang, Y.; Xie, Z.; Wang, X.; Peng, X.; Zheng, J. Fluorescent Carbon-Dots Enhance Light Harvesting and Photosynthesis by Overexpressing PsbP and PsiK Genes. J. Nanobiotechnol.
**2021**, 19, 260. [Google Scholar] [CrossRef] - Ponzoni, F.J.; Shimabukuro, Y.E.; Kuplich, T.M. Sensoriamento Remoto Da Vegetação, 2nd ed.; Oficina de Textos: São Paulo, Brazil, 2012; ISBN 978-85-7975-053-3. [Google Scholar]
- dos Santos, N.V.; Demattê, J.A.M.; Silvero, N.E.Q. Improving the Monitoring of Sugarcane Residues in a Tropical Environment Based on Laboratory and Sentinel-2 Data. Int. J. Remote Sens.
**2020**, 42, 1768–1784. [Google Scholar] [CrossRef] - Chandel, N.S.; Rajwade, Y.A.; Golhani, K.; Tiwari, P.S.; Dubey, K.; Jat, D. Canopy Spectral Reflectance for Crop Water Stress Assessment in Wheat (Triticum aestivum, L.). Irrig. Drain.
**2020**, 70, 321–331. [Google Scholar] [CrossRef] - Chen, H.; Wang, P.; Li, J.; Zhang, J.; Zhong, L. Canopy Spectral Reflectance Feature and Leaf Water Potential of Sugarcane Inversion. Phys. Procedia
**2012**, 25, 595–600. [Google Scholar] [CrossRef] - Gates, D.M.; Keegan, H.J.; Schleter, J.C.; Weidner, V.R. Spectral Properties of Plants. Appl. Opt.
**1965**, 4, 11. [Google Scholar] [CrossRef] - Muller, S.J.; Sithole, P.; Singels, A.; Van Niekerk, A. Assessing the Fidelity of Landsat-Based FAPAR Models in Two Diverse Sugarcane Growing Regions. Comput. Electron. Agric.
**2020**, 170, 105248. [Google Scholar] [CrossRef] - Zhang, F.; Zhou, G. Estimation of Vegetation Water Content Using Hyperspectral Vegetation Indices: A Comparison of Crop Water Indicators in Response to Water Stress Treatments for Summer Maize. BMC Ecol.
**2019**, 19, 18. [Google Scholar] [CrossRef] [PubMed] - Jamshidi, S.; Zand-Parsa, S.; Pakparvar, M.; Niyogi, D. Evaluation of Evapotranspiration over a Semiarid Region Using Multiresolution Data Sources. J. Hydrometeorol.
**2019**, 20, 947–964. [Google Scholar] [CrossRef] - Nisa, Z.; Khan, M.S.; Govind, A.; Marchetti, M.; Lasserre, B.; Magliulo, E.; Manco, A. Evaluation of SEBS, METRIC-EEFlux, and QWaterModel Actual Evapotranspiration for a Mediterranean Cropping System in Southern Italy. Agronomy
**2021**, 11, 345. [Google Scholar] [CrossRef] - Ortega-Salazar, S.; Ortega-Farías, S.; Kilic, A.; Allen, R. Performance of the METRIC Model for Mapping Energy Balance Components and Actual Evapotranspiration over a Superintensive Drip-Irrigated Olive Orchard. Agric. Water Manag.
**2021**, 251, 106861. [Google Scholar] [CrossRef]

**Figure 1.**Location of the study area with the central pivots used for training, testing, and applying the models highlighted.

**Figure 2.**Climatological normal of the study region extracted from station 83,386 of INMET (Instituto Nacional de Meteorologia).

**Figure 3.**Acquisition of data from sensors onboard Landsat-8 and Sentinel-2 for training and testing in machine learning algorithms.

**Figure 4.**Statistical results for the selection of predictor variables when applying the RFE in approach 1.

**Figure 5.**Statistical results for the selection of predictor variables when applying the RFE in approach 2.

**Figure 10.**Comparison of K

_{c}values between approaches 1 and 2, METRIC, and the ones recommended by the FAO’s 56 reports.

**Figure 11.**Sugar cane temporal-spatial actual evapotranspiration in three different spatial resolutions evincing, through rectangles, coincident dates between Sentinel-2 and Landsat-8.

Spectral Band | Wavelength (μm) | Spatial Resolution (m) | |
---|---|---|---|

OLI | |||

B1 | Coastal aerosol (Ca) | 0.43–0.45 | 30 |

B2 | Blue (B) | 0.45–0.51 | |

B3 | Green (G) | 0.53–0.59 | |

B4 | Red (R) | 0.64–0.67 | |

B5 | Near-infrared (NIR) | 0.85–0.88 | |

B6 | Shortwave infrared 1 (SWIR1) | 1.57–1.65 | |

B7 | Shortwave infrared 2 (SWIR2) | 2.11–2.29 | |

B8 | Panchromatic (PCh) | 0.50–0.68 | |

B9 | Cirrus (C) | 1.36–1.38 | |

TIRS | |||

B10 | Thermal infrared 1 (TIRS1) | 10.60–11.19 | 100 * |

B11 | Thermal infrared 2 (TIRS2) | 11.50–12.51 |

Spectral Band | Wavelength (μm) | Spatial Resolution (m) | |
---|---|---|---|

MSI | |||

B2 | Blue (B) | 0.459–0.525 | 10 |

B3 | Green (G) | 0.542–0.578 | |

B4 | Red (R) | 0.650–0.680 | |

B8 | Near-infrared (NIR) | 0.781–0.887 | |

B5 | red edge 1 (Re1) | 0.697–0.712 | 20 |

B6 | red edge 2 (Re2) | 0.733–0.748 | |

B7 | red edge 3 (Re2) | 0.773–0.793 | |

B8A | Near-infrared narrow (NIRn) | 0.856–0.876 | |

B11 | Shortwave infrared 1 (SWIR1) | 1.569–1.660 | |

B12 | Shortwave infrared 2 (SWIR2) | 2.115–2.290 | |

B1 | Coastal aerosol | 0.433–0.453 | 60 |

B9 | Water vapor | 0.935–0.955 | |

B10 | Cirrus | 1.359–1.390 |

Date (mm/dd/aaaa) | Landsat-8 | Sentinel-2 | ||
---|---|---|---|---|

Time (hh:mm:ss) | Path/Row | Time (hh:mm:ss) | Tile Number | |

Training and Test | ||||

07/06/2018 | 09:55:17.157 | 218/71 | 10:12:41.024 | T23LPD |

05/22/2019 | 09:55:49.714 | 218/71 | 10:12:51.024 | T23LPD |

10/04/2019 | 10:02:19.874 | 219/70 | 10:12:49.024 | T23LPD |

10/29/2019 | 09:56:34.656 | 218/71 | 10:12:49.024 | T23LPD |

01/17/2020 | 09:56:20.969 | 218/71 | 10:12:41.024 | T23LPD |

05/31/2020 | 10:01:27.427 | 219/70 | 10:12:49.024 | T23LPD |

08/19/2020 | 10:02:00.995 | 219/70 | 10:12:49.024 | T23LPD |

Residual analysis | ||||

12/02/2020 | 09:56:32.117 | 218/71 | 10:12:41.024 | T23LPD |

N° | Approach 1 | Approach 2 |
---|---|---|

1 | B2 | B6 |

2 | B4 | B8 |

3 | B8 | B12 |

4 | (B2 − B3)/(B2 + B3) | (B2 − B3)/(B2 + B3) |

5 | (B2 − B4)/(B2 + B4) | (B2 − B4)/(B2 + B4) |

6 | - | (B2 − B5)/(B2 + B5) |

7 | - | (B2 − B12)/(B2 + B12) |

8 | - | (B5 − B11)/(B5 + B11) |

9 | - | (B5 − B12)/(B5 + B12) |

10 | - | (B6 − B8)/(B6 + B8) |

11 | - | (B8 − B12)/(B8 + B12) |

12 | - | (B11 − B12)/(B11 + B12) |

DAE | Approach 1 | Approach 2 | METRIC | Difference (%) | |
---|---|---|---|---|---|

(mm) | (mm) | (mm) | Approach 1 | Approach 2 | |

060 | 6.71 ± 0.44 | 6.63 ± 0.36 | 6.75 ± 0.25 | 0.59 | 1.77 |

195 | 4.52 ± 0.22 | 4.48 ± 0.09 | 4.78 ± 0.06 | 5.44 | 6.28 |

220 | 4.25 ± 0.21 | 4.68 ± 0.11 | 4.79 ± 0.08 | 11.27 | 2.30 |

275 | 3.75 ± 0.36 | 4.32 ± 0.20 | 4.44 ± 0.17 | 16.54 | 2.77 |

ET-Total | 1417.77 | 1474.26 | 1544.11 | 8.18 | 4.52 |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

dos Santos, R.A.; Mantovani, E.C.; Fernandes-Filho, E.I.; Filgueiras, R.; Lourenço, R.D.S.; Bufon, V.B.; Neale, C.M.U.
Modeling Actual Evapotranspiration with MSI-Sentinel Images and Machine Learning Algorithms. *Atmosphere* **2022**, *13*, 1518.
https://doi.org/10.3390/atmos13091518

**AMA Style**

dos Santos RA, Mantovani EC, Fernandes-Filho EI, Filgueiras R, Lourenço RDS, Bufon VB, Neale CMU.
Modeling Actual Evapotranspiration with MSI-Sentinel Images and Machine Learning Algorithms. *Atmosphere*. 2022; 13(9):1518.
https://doi.org/10.3390/atmos13091518

**Chicago/Turabian Style**

dos Santos, Robson Argolo, Everardo Chartuni Mantovani, Elpídio Inácio Fernandes-Filho, Roberto Filgueiras, Rodrigo Dal Sasso Lourenço, Vinícius Bof Bufon, and Christopher M. U. Neale.
2022. "Modeling Actual Evapotranspiration with MSI-Sentinel Images and Machine Learning Algorithms" *Atmosphere* 13, no. 9: 1518.
https://doi.org/10.3390/atmos13091518