When linking explanatory and response variables, the outcome can be either classification or regression. In classification problems, the output would be a prediction/classification of discrete values. For instance, based on all input data, trees could be classified into healthy and diseased groups. On the other hand, regression algorithms are used to predict the continuous values, such as the amount of yield in an orchard. For both classification and regression several methods are available and for each method some statistical criteria assess the accuracy. However, linear regression, due to its simplicity and interpretability has gained a lot of attention and is implemented in numerous studies. Table 5 includes explanatory variable, response variable and modeling methods used in the selected papers that are focused on remote sensing application for nut crops discussed in previous sections. As it is shown in the table, more than 70 percent of the papers have used linear regression as a primary, or in some cases secondary, modeling method.
In general, analysis methods can be categorized into two general classes of linear and nonlinear algorithms. Among linear algorithms, simple (one input variable) and multiple (multiple input variables) linear regressions (MLR) are the most common methods utilized in numerous agricultural studies for predicting yield, LAI , stem water potential, nitrogen status, and many more. MLR has attracted lots of attention especially since it can be combined with the feature selection step to select the most contributing factors and the best model at the same time. Forward Selection, Backward Elimination, and Stepwise Selection are the highly reported methods that evaluate the model step by step based on their statistical significance and contribution to the response variable's variance (Regression Sum of Squares). For a limited number of input variables, linear regressions are very reliable, and the relationship between the input variables and the response can be easily interpreted. However, in some remote sensing studies, especially recent publications that include several sensors, many variables are extracted to predict a response factor and the increasing number of explanatory variables makes the MLR model selection process more challenging. Moreover, many agricultural processes are better represented by nonlinear models than linear models. As a result, alternatives to linear approaches, such as computational methods, emerged regardless of their complexity and lack (or difficulty) of interpretability.
Table 6 - Analysis parameters of the selected papers
1- Enhanced Bloom Index
2- Support Vector Machine- Classification
3- The standard deviation of temperature
4- Differential between canopy and air temperature
5- Days Since Last Irrigation
6- Linear Discriminant Analysis
7- Solar-induced fluorescence
8- Vapor Pressure Deficit
9- The Water Index (WI), NDWI, The Normalized Difference Infrared Index (NDII)
10- Canopy Water Content
11- Historic yield, orchard age, temperature, NDVI, etc.
12- Machine Learning
13- land surface temperature
14- Mapping Evapotranspiration at high Resolution with Internalized Calibration (Inputs: NDVI, LST, Albedo, LAI)
15- Digital Elevation Mode
Computational intelligence (artificial intelligence) and expert systems, such as Artificial Neural Networks (ANN) or more advanced machine learning methods, which are considered a subdivision of nonlinear algorithms, have gained increasing attention due to several reasons: their ability to handle quantitative and qualitative data simultaneously, their capacity to weight variables based on their importance, their potential to manage both linear and nonlinear responses, and the growing computational power of new computers. Since these methods use their internal transformations (through weights and activation functions), an optimal combination of the features (engineered features) will be formed inside the algorithms, making these techniques a powerful modeling tool in many fields. Methods such as ANN, Regression (decision) Trees (RT) , Partial Least Squares Regression (PLSR) , and Random Forest (RF) are widely utilized in agricultural fields. However, regardless of their outstanding success in different areas, artificial intelligence methods need a relatively large number of samples (labels) that dwarfs their advantage in most remote sensing applications. As a result, finding a technique that combines artificial intelligence with other statistical methods to preserve AI methods' advantages while minimizing their need for large amounts of samples is of broad and current interest.
As we discussed throughout this paper, due to the dynamic and complex nature of agricultural environments, numerous factors can affect the response variable to a certain extend. Moreover, remote sensing data might have different spectral, spatial, and temporal resolutions. An ambitious model should take all the determining factors into account, weight them based on their importance level, and use all available information so that the combination of inputs can represent a more accurate prediction. To reach such a model, a data fusion framework is needed to combine data from various layers of information to fill the knowledge gap.
 J. L. Zarate-Valdez, S. Muhammad, S. Saa, B. D. Lampinen, and P. H. Brown, “Light interception, leaf nitrogen and yield prediction in almonds: a case study,” European Journal of Agronomy, vol. 66, pp. 1–7, 2015.
 R. Colombo, D. Bellingeri, D. Fasolini, and C. M. Marino, “Retrieval of leaf area index in different vegetation types using high resolution satellite data,” Remote Sensing of Environment, vol. 86, no. 1, pp. 120–131, 2003.
 L. E. Williams and F. J. Araujo, “Correlations among predawn leaf, midday leaf, and midday stem water potential and their correlations with other measures of soil and plant water status in Vitis vinifera,” Journal of the American Society for Horticultural Science, vol. 127, no. 3, pp. 448–454, 2002.
 L. Xue, W. Cao, W. Luo, T. Dai, and Y. Zhu, “Monitoring leaf nitrogen status in rice with canopy spectral reflectance,” Agronomy Journal, vol. 96, no. 1, pp. 135–142, 2004.
 S. V. Archontoulis and F. E. Miguez, “Nonlinear regression models and applications in agricultural research,” Agronomy Journal, vol. 107, no. 2, pp. 786–798, 2015.
 T. Zhao, B. Stark, Y. Q. Chen, A. L. Ray, and D. Doll, “Challenges in Water Stress Quantification Using Small Unmanned Aerial System (sUAS): Lessons from a Growing Season of Almond,” Journal of Intelligent and Robotic Systems: Theory and Applications, vol. 88, no. 2–4, pp. 721–735, Dec. 2017, doi: 10.1007/s10846-017-0513-x.
 K. E. Crawford, “Remote Sensing of Almond and Walnut Tree Canopy Temperatures Using an Inexpensive Infrared Sensor on a Small Unmanned Aerial Vehicle,” University of California, Davis, California, Davis, 2014.
 F. López-Granados, J. Torres-Sánchez, F. M. Jiménez-Brenes, O. Arquero, M. Lovera, and A. I. de Castro, “An efficient RGB-UAV-based platform for field almond tree phenotyping: 3-D architecture and flowering traits,” Plant Methods, vol. 15, no. 1, pp. 1–16, 2019.
 J. Torres-Sánchez et al., “Mapping the 3D structure of almond trees using UAV acquired photogrammetric point clouds and object-based image analysis,” Biosystems engineering, vol. 176, pp. 172–184, 2018.
 S. Y. Erfanifard, A. Chenari, M. Dehghani, and F. Amiraslani, “Effect of spatial resolution of UAV aerial images on height estimation of wild pistachio (Pistacia atlantica Desf.) trees.,” Iranian Journal of Forest and Poplar Research, vol. 27, no. 2, 2019.
 B. Chen, Y. Jin, and P. Brown, “An enhanced bloom index for quantifying floral phenology using multi-scale remote sensing observations,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 156, pp. 108–120, 2019.
 V. Gonzalez-Dugo, P. Zarco-Tejada, J. A. J. Berni, L. Suárez, D. Goldhamer, and E. Fereres, “Almond tree canopy temperature reveals intra-crown variability that is water stress-dependent,” Agricultural and Forest Meteorology, vol. 154–155, p. 156, 2012, doi: 10.1016/j.agrformet.2011.11.004.
 V. Gonzalez-Dugo et al., “Using high resolution UAV thermal imagery to assess the variability in the water status of five fruit tree species within a commercial orchard,” Precision Agriculture, vol. 14, no. 6, pp. 660–678, Dec. 2013, doi: 10.1007/s11119-013-9322-9.
 V. Gonzalez-Dugo, D. Goldhamer, P. J. Zarco-Tejada, and E. Fereres, “Improving the precision of irrigation in a pistachio farm using an unmanned airborne thermal system,” Irrigation science, vol. 33, no. 1, pp. 43–52, 2015.
 M. López-López, R. Calderón, V. González-Dugo, P. Zarco-Tejada, and E. Fereres, “Early Detection and Quantification of Almond Red Leaf Blotch Using High-Resolution Hyperspectral and Thermal Imagery,” Remote Sensing, vol. 8, no. 4, p. 276, Mar. 2016, doi: 10.3390/rs8040276.
 C. Camino, P. Zarco-Tejada, and V. Gonzalez-Dugo, “Effects of heterogeneity within tree crowns on airborne-quantified SIF and the CWSI as indicators of water stress in the context of precision agriculture,” Remote Sensing, vol. 10, no. 4, p. 604, 2018.
 J. Bellvert, K. Adeline, S. Baram, L. Pierce, B. L. Sanden, and D. R. Smart, “monitoring crop evapotranspiration and crop coefficients over an almond and pistachio orchard throughout remote sensing,” Remote Sensing, vol. 10, no. 12, Dec. 2018, doi: 10.3390/rs10122001.
 S. Roy and D. Ophori, “Estimation of crop water stress index in almond orchards using thermal aerial imagery.,” Journal of Spatial Hydrology, vol. 12, no. 1, 2014.
 T. Cheng, D. Riaño, and S. L. Ustin, “Detecting diurnal and seasonal variation in canopy water content of nut tree orchards from airborne imaging spectroscopy data using continuous wavelet analysis,” Remote Sensing of Environment, vol. 143, pp. 39–53, Mar. 2014, doi: 10.1016/j.rse.2013.11.018.
 Z. Zhang, Y. Jin, B. Chen, and P. Brown, “California almond yield prediction at the orchard level with a machine learning approach,” Frontiers in plant science, vol. 10, p. 809, 2019.
 H. Li, C. Zhang, S. Zhang, and P. M. Atkinson, “Full year crop monitoring and separability assessment with fully-polarimetric L-band UAVSAR: A case study in the Sacramento Valley, California,” International Journal of Applied Earth Observation and Geoinformation, vol. 74, pp. 45–56, Feb. 2019, doi: 10.1016/j.jag.2018.08.024.
 S. W. Shivers, D. A. Roberts, and J. P. McFadden, “Using paired thermal and hyperspectral aerial imagery to quantify land surface temperature variability and assess crop stress within California orchards,” Remote Sensing of Environment, vol. 222, pp. 215–231, Mar. 2019, doi: 10.1016/j.rse.2018.12.030.
 Y. Jin et al., “Spatially variable evapotranspiration over salt affected pistachio orchards analyzed with satellite remote sensing estimates,” Agricultural and Forest Meteorology, vol. 262, pp. 178–191, Nov. 2018, doi: 10.1016/j.agrformet.2018.07.004.
 R. He et al., “Evapotranspiration estimate over an almond orchard using landsat satellite observations,” Remote Sensing, vol. 9, no. 5, p. 436, 2017.
 H. Fadaei, T. Sakai, and K. Torii, “Investigation on pistachio distribution in the mountain regions of northeast Iran by ALOS,” Front. Agric. China, vol. 5, no. 3, p. 393, Sep. 2011, doi: 10.1007/s11703-011-1108-0.
 X. E. Pantazi, D. Moshou, T. Alexandridis, R. L. Whetton, and A. M. Mouazen, “Wheat yield prediction using machine learning and advanced sensing techniques,” Computers and electronics in agriculture, vol. 121, pp. 57–65, 2016.
 B. Schreck, “Feature Engineering vs Feature Selection,” Alteryx Innovation Labs, 2018. https://innovation.alteryx.com/feature-engineering-vs-feature-selection/ (accessed Jan. 09, 2021).
 A. Moghimi, C. Yang, and J. A. Anderson, “Aerial hyperspectral imagery and deep neural networks for high-throughput yield phenotyping in wheat,” Computers and Electronics in Agriculture, vol. 172, p. 105299, 2020.
 H. Zheng, L. Chen, X. Han, X. Zhao, and Y. Ma, “Classification and regression tree (CART) for analysis of soybean yield variability among fields in Northeast China: The importance of phosphorus application rates under drought conditions,” Agriculture, Ecosystems & Environment, vol. 132, no. 1–2, pp. 98–105, 2009.
 I. Herrmann, E. Bdolach, Y. Montekyo, S. Rachmilevitch, P. A. Townsend, and A. Karnieli, “Assessment of maize yield and phenology by drone-mounted superspectral camera,” Precision Agriculture, vol. 21, no. 1, pp. 51–76, 2020.
 Z. Fu et al., “Wheat growth monitoring and yield estimation based on multi-rotor unmanned aerial vehicle,” Remote Sensing, vol. 12, no. 3, p. 508, 2020.