# Deep Learning to Improve the Sustainability of Agricultural Crops Affected by Phytosanitary Events: A Financial-Risk Approach

^{1}

^{2}

^{3}

^{4}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Literature Review

- A first development trend focuses on the use of multi (MIs) and hyper-spectral (HIs) images for the non-destructive phytosanitary diagnosis of crops in situ [21]. A first group of papers shows how MAIs have helped detect phytosanitary events. As proof of this, ref. [22] identified the impact of Mildiu on leaves in tomato cultivation, and ref. [23] characterised the yellow striation on maize crops. Finally, ref. [24] determined the biochemical characteristics and physiological features of PEs in wheat crops. In this same group, ref. [25] showed how MAIs have been used to assess the productivity of macadamia trees. A second group of papers focuses on MAIs to improve risk management in oil-palm crops. In this way, ref. [26] described the relevance of MAIs and VIs for precision farming in oil-palm crops, ref. [27] described the use of advanced classifiers for the diagnosis of healthy oil-palm units from MAIs. Finally, ref. [28] showed a methodology for the use of MAIs to characterise PEs in different crops. This development trend shows how recent advances in optical remote sensing, including camera systems and spectral data analysis, allow the non-destructive diagnosis of phytosanitary events (PEs), improving the process of detecting diseases in crops. Although satellite images (Sis) are an excellent alternative for the monitoring and characterisation of PEs in oil-palm crops located over large areas of land, the frequency for capturing, the required resolution, and the associated costs for processing these images is a barrier to decision makers [29].
- A second development trend focuses on designing vegetation indices (VIs) using multi-spectral images (MIs). The NDVI (Normalised difference vegetation index) is one of the most cited, e.g., in the area of evaluating the plant vigour in areas of considerable agricultural coverage [30]. This index is also used in combination with others, such as GNDVI (green normalised difference) and SAVI (soil adjusted), to determine plant vigour in vineyards and tomato crops [26]. While some authors have discussed the applicability of MIs for the diagnosis of vegetation states in different agriculture crops [22], others have developed VIs by using just MIs, obtaining satisfactory results. Some researchers have developed VIs based on multi-spectral aerial images (MAIs) taken with unmanned aerial vehicles (UAVs), e.g., for the spatial characterisation of oil-palm crops [27], and for the detection and diagnosis of phytosanitary states in different crops [28]. In addition, these MAIs have been used for the identification of fruits in coffee crops [23], for the treatment of weeds [31] and for the control of deforestation processes [32]. It is essential to highlight the preponderance achieved by the MAIs for diagnosing crop health, overcoming the limitations of SIs in monitoring units for different crops. It is also necessary to highlight the technological development of hyperspectral images (HIs); however, the creation of VIs for the diagnosis of PEs using this technology is still at a very early stage of development [18].
- A third development trend focuses on creating augmented-intelligence platforms (AIPs) to improve the real-time characterisation of crops. These platforms aim to integrate different technologies for the diagnosis of PEs, among which RGB (red-green-blue) and MI images, and ML and DL models, stand out [33,34,35]. Other researchers have pushed these platforms by integrating IoT (Internet of Things) devices, such as optical and multi-spectral sensors and technologies for communication (LORA, Zigbee). In this way, ref. [36] mapped arctic vegetation, ref. [19] showed the ecological monitoring of open-space species, and ref. [37] improved the autonomy of unmanned aerial vehicles (UAVs), identifying disease hot spots located over large areas of crops, supported by ML and DL models. Within ML and DL modelling to support AIPs in monitoring crops, ref. [38] presented a convolutional neural model (CNN) to detect pine trees affected by wilt using MAIs, and ref. [39] presented a set of ML algorithms to improve irrigation process in vineyards also using MAIs. Finally, ref. [40] presented a preliminary analysis of pathology detection in oil-palm crops using convolutional neural networks (CNN) integrating MAIs and VIs. Finally, ref. [40] presents a preliminary analysis of pathology detection in oil-palm crops using convolutional neural networks (CNN) integrating MAIs and VIs. This development trend shows how AIPs have enabled efficient real-time crop management by integrating IOT technologies. However, it can be observed that there is an absence of AIPs that integrate models for adaptation and learning to identify the dispersion dynamics or for the characterisation of risks derived from a PE in crops.
- A fourth development trend focuses on the design of parametric insurances based on the characterisation of operational risk (OR) for different management scenarios [41]. Within this trend, the first group of studies shows how the ML concepts have been used to model OR [42]. Some researchers have defined fuzzy-inference models for the qualitative description of scenarios for OR management [8] or to determine the inherent risk as a result of implementing different management scenarios when mitigating OR [43]. In addition, the estimation of this risk through the integration of multi-dimensional databases is available in [9]. Within this trend, a second group of studies focuses on the configuration of parametric insurances in developing countries [44]. The first study presents a series of recommendations to achieve the sustainability of oil-palm crops through the characterisation and identification of operational and reputational risks [45]. In contrast, a second study shows the configuration of parametric insurances concerning risk related to changing weather conditions [46]. Furthermore, it has been demonstrated how insurance contracts can be designed based on a farmer satisfaction index by integrating statistical analysis of agro-climatic data and by applying optimisation techniques for improving the coverage for catastrophic risks [47]. Ref. [48] shows how neural networks have been used for credit-risk modelling by analysing the relationship between access to credit and productivity in the agricultural sector for a large set of countries. Due to the importance of OR in the design of insurance products for the protection of farming activities, in this development trend, as in the case of the previous trend, it is observed that there is an absence of models integrating ML and financial-risk concepts for the improvement of the environmental and financial sustainability of crops [20].

#### 2.1. Theory And Definitions

#### 2.1.1. Operational Risk

#### 2.1.2. Aggregate Loss Distribution (ALD):

- Expected losses (EL): EL losses are known as predictable losses and represent the group of losses that an organisation can assume. The mean of the ALD establishes the upper limit for this type of losses.
- Stress losses (SL): SL refers to the group of losses that generate a significant deterioration of the assets of an organisation (catastrophic or restorative losses). The operational value at Risk (OpVar) represents these losses, which is located at the $99.9\%$ percentile of the ALD. The OpVar represents the insurable value to protect the assets of an organisation.
- Unexpected losses (UL): UL refers to the group of losses that are located between the EL limit and the OpVar value. These losses are known as manageable losses.

- In the context of oil-palm crops, an event risk is quantified as the convolution between the frequency (number of crops affected by LW) and the severity (cost of eradication and treatment of oil palm units, e.g., insecticides) in a period (usually one day).
- The difference between EL and SL losses leads to evaluating the environmental and financial sustainability of crops affected by a phytosanitary or an agro-climate event (sustainability GAP ($S-GAP$)).
- Under the Basel III agreement, the ALD distribution is known as the loss component (LC) [50].

#### 2.1.3. Log-Logistic Distribution

- ${z}_{jc}$ represents the cumulative probability distribution (CDF) for a risk category ${j}_{c}$.
- $\alpha $: dimensional factor (dcale parameter).
- $\beta $: structural factor (shape parameter).
- a: stability factor (lower limit for the mean).

## 3. Materials and Methods

#### 3.1. Experimental Study Design

#### 3.2. Adaptive Inverse Lagrangian Gaussian Model

#### 3.3. Dispersion Pattern (Dynamic 1)

- $Q{m}_{x,y}$ indicates the intensity of LW at the point $\left(x,y\right)$ (m).
- ${x}_{f},{y}_{f}$ indicates the location of the focus within the pattern of dispersion (m).
- ${\sigma}_{xy}$: dispersion coefficient that indicates the area of influence of LW in the field from a focus of the disease $\left({x}_{f},{y}_{f}\right)$ (m).

- x: diameter measured from the point of location of the dispersion pattern $({x}_{p},{y}_{p})$ taking as reference one hectare (ha) of crop (m).
- $a,b$: dispersion parameters that describe the evolution of LW in the study zone (LW-affectation). Figure 4 shows the upward curves of LW dispersion for different dynamics.

- To achieve reliability of $99.9\%$ in the characterisation of LW-affectation in the field, a total of $6.9$ ha ($144\phantom{\rule{4pt}{0ex}}\mathrm{un}/\mathrm{ha}\times 6.9\phantom{\rule{4pt}{0ex}}\mathrm{ha}=1000\phantom{\rule{4pt}{0ex}}\mathrm{un}$) were taken as reference. Based on a circular dispersion pattern, the linear radius of coverage will be close to 150 m (70,685.82 ${\mathrm{m}}^{2}=\pi .{\left(150\phantom{\rule{4pt}{0ex}}\mathrm{m}\right)}^{2}$).
- For the configuration of the disease focus, a canopy ring consisting of 12 crop units was taken as a reference. This canopy ring has an approximate linear radius coverage of 10 m ($x\phantom{\rule{4pt}{0ex}}\phantom{\rule{4.pt}{0ex}}\left(\mathrm{m}\right)$).
- For stability of the model against the identification and characterisation of LW in the field, this dispersion coefficient performs an automatic normalisation process against disease progress (upward curves).
- To model the dispersion of LW in the field, a disease development rate of $0.0833\phantom{\rule{4pt}{0ex}}\mathrm{un}/\mathrm{year}$ (r) was taken as reference for an approximate lot size of $25\phantom{\rule{3.33333pt}{0ex}}\mathrm{ha}$ ($144\phantom{\rule{4pt}{0ex}}\mathrm{un}/\mathrm{ha}\times \phantom{\rule{4pt}{0ex}}25\phantom{\rule{4pt}{0ex}}\mathrm{un}=3600\phantom{\rule{4pt}{0ex}}\mathrm{un}$).
- To achieve a theoretical lot coverage for LW, a period of (6) months was taken. For this period, the rate of disease (r) development resulted in approximately $150\phantom{\rule{3.33333pt}{0ex}}\mathrm{un}$ affected crop units, as described in the reference (Scenario 1).

#### 3.4. LW-Affectation (Dynamic 2)

- $MCO{P}_{x,y}$: LW-affectation of the point $\left(x,y\right)$ given a dispersion pattern $Q{m}_{x,y}$.
- ${\sigma}_{xy,p}$: Compression coefficient (inverse dispersion) for an MCOP located at the point $\left({x}_{p},{y}_{p}\right)$. This compression coefficient is denoted and defined as follows:$${\sigma}_{xy,p}=-ks.\left(\frac{1}{a.{x}^{-b}}\right)$$

- $ks$ indicates the size of an MCOP in the standardised space (Study Zone). According to the initial size of the dispersion pattern ($Q{m}_{x,y}$), an MCOP will have a length approximately of $10\%$ ($ks=0.4\phantom{\rule{4pt}{0ex}}\times \phantom{\rule{4pt}{0ex}}10\%$) of the spatial coverage by this pattern.

#### 3.5. Lagrangian Hybrid Deep-Learning Model (Lg-Hdlm)

#### 3.5.1. Stacked Deep-Learning Structure (Substructure 1)

- ${x}_{{j}_{0}}$ represents the input vector or k cropped image (CI) ($k=1,2,\dots ,ND$). Each of the CIs has a size of $\left(300\phantom{\rule{4pt}{0ex}}\mathrm{px}\times 300\phantom{\rule{4pt}{0ex}}\mathrm{px}\right)$ per MAI or VI.
- $ND$ represents the number of CIs available for the configuration of the model.
- ${w}_{{j}_{n},{j}_{n}-1}$ represents the neural connections between the ${j}_{n}$ and the ${j}_{n-1}$ layer.
- $n{o}_{n}$ indicates the number of hidden elements or neurons that make up the n layer.
- ${h}_{{j}_{n}}$ represents each of the ${j}_{n}$ outputs of the $n{o}_{n}$ neurons that make up a hidden n layer.

- $n{o}_{n}$: number of hidden neurons for the n$layer$.
- $nl$: number of stacked layers (cardinality) ($n=1,2,\dots ,nl$).
- $n{o}_{max}$: maximum number of neurons for the $1st$$layer$ (compression ratio).

- Cardinality: Indicates the number of stacked layers that make up a deep-learning neural model of the stacked type. Higher cardinality leads to greater flexibility in modelling complex systems, bringing higher computational costs.
- Compression Ratio: Indicates the compression capacity of each layer that makes up a neural deep-learning model by stacked layers when configured using auto-encoder strategies. The compression ratios performed by the first stacked layer for these models determine its behaviour in modelling complex systems.

- ${e}_{k}^{2}$ represents the mean square error (e.g., mse), which is expressed as:

- ${x}_{{j}_{{n}_{l}-2},k}$: Represents the input and output values used as a reference for the configuration of the ${n}_{l}$ hidden layers that build the stacked structure of the proposed model.

- ${c}_{{j}_{c},{j}_{{n}_{l}}}$ represents the FCL connections.

- ${j}_{c}$: labelling categories (MCOP, non-MCOP) ${j}_{c}:1,2,\dots ,{k}_{c}$.
- ${z}_{{j}_{c}}$: probability associated with a ${j}_{c}$$category$.

#### 3.5.2. Convolutional Lagrangian Gaussian Deep-Learning Model (Substructure 2)

- $X{C}_{j,x},X{C}_{j,y}$: relative position for a j$crop$ unit in the field.
- ${x}_{j,k},{y}_{j,k}$ indicates the spatio-temporal spread of LW from a j crop unit and a k $instant$ time.
- ${\sigma}_{j,x,k},{\sigma}_{j,y,k}$: Dispersion coefficients that determine the dynamic of LW-affectation from a $X{C}_{j,x,k},X{C}_{j,y,k}$ spatial point. These coefficients can be modelled based on phytosanitary censuses for LW-affectation carried out in the field for the period defined for this study.

- $\mathsf{\Phi}\left({x}_{j,k},{y}_{j,k},l\right)$: Vector of agreement indices between a Gaussian-MCOP pattern (${j}_{c}$ risk category) for each of the points (${x}_{j,k},{y}_{j,k}$) that make up a l convolutional layer (IC-fingerprint).
- $MCO{P}_{{x}_{{j}_{r}},{y}_{{j}_{r}},l,{j}_{c},k}$: Convolutional Gaussian-MCOP pattern for a l MAI or l VI, a ${j}_{c}$ risk category for a k instant time. The convolutional Gaussian-MCOP patterns will be selected from Scenario 1 by LW-affectation.
- ${j}_{ic}$ represents the ${j}_{ic}$ agreement index. For the characterisation of oil-palm units by LW-affectation based on Gaussian-MCOP patterns, we propose the following agreement indices [64]:
- $IO{A}_{l,k}$: Index of agreement between a spatial oil palm and a $MCO{P}_{{x}_{{j}_{r}},{y}_{{j}_{r}},l,{j}_{c},k}$ convolutional pattern.
- $M{G}_{l,k}$: Geometric mean bias between a spatial oil palm and a $MCO{P}_{{x}_{{j}_{r}},{y}_{{j}_{r}},l,{j}_{c},k}$ convolutional pattern.
- $V{G}_{l,k}$: Geometric variance bias between a spatial oil palm and a $MCO{P}_{{x}_{{j}_{r}},{y}_{{j}_{r}},l,{j}_{c},k}$ convolutional pattern.

- ${\sigma}_{LLG}\left({z}_{{j}_{c}}\right)$: log-logistic Softmax function for the classification of crop units in the ${j}_{c}$ risk category (Equation (13)).
- ${c}_{{j}_{c},{j}_{ic}}$: Represents the FCL connections for a ${j}_{c}$ risk category and ${j}_{ic}$ index of agreement.

#### 3.6. Metrics

#### 3.6.1. Accuracy Weighted Index (Acc-w)

- ${w}_{{j}_{c}}$ represents the weighted effect of the number of data that belongs to a category ${j}_{c}$.
- $T{P}_{{j}_{c}}$: true positive number of data that are correctly identified by a model for a ${j}_{c}$ category.
- $T{N}_{{j}_{c}}$: true negative number of data that are erroneously identified by a model for category ${j}_{c}$.

#### 3.6.2. Categorical Cross Entropy (CCE)

- ${\widehat{y}}_{k}$: Represents the value predicted by the model for observation k.
- $y{d}_{k}$: Value of reference or desired value for observation k.
- $ND$: Total of samples of data or MCOPs available ($k=1,2,3,\dots ,ND$).

- For classification and labelling, this metric will allow evaluating the performance of the LG-HDLM (Substructure 1) against the classification and labelling of CIs in the categories of MCOPs and non-MCOPs reflectance band and VI.
- For the discrete-risk classification, this metric will allow evaluating the performance of LG-HDLM (Substructure 2) against the classification of MCOPs by loss category, according to the loss structure defined by ALD.
- For the continuous-risk characterisation, this metric will assess the stability of LG-HDLM against the characterisation of ALD structure by risk scenario, according to the probabilities assigned by the Softmax function for each of the MCOPs classified by risk category.

#### 3.7. Dimensional and Structural Stability

#### 3.8. Mean Square Error (mse)

- $y{d}_{{j}_{c},k}$: indicates the reference values to set-up and adaptive models for k$record$ and ${j}_{c}$ $category$.
- ${\widehat{y}}_{{j}_{c},k}$: indicates the value estimated by an adaptive model for k$record$ and ${j}_{c}$ $category$.

#### 3.9. Experimental Validation

## 4. Results

## 5. Conclusions and Further Studies

## Author Contributions

## Funding

## Acknowledgments

## Conflicts of Interest

## References

- Chopra, R.; Magazzino, C.; Shah, M.I.; Sharma, G.D.; Rao, A.; Shahzad, U. The role of renewable energy and natural resources for sustainable agriculture in ASEAN countries: Do carbon emissions and deforestation affect agriculture productivity? Resour. Policy
**2022**, 76, 102578. [Google Scholar] [CrossRef] - Maluin, F.N.; Hussein, M.Z.; Idris, A.S. An Overview of the Oil Palm Industry: Challenges and Some Emerging Opportunities for Nanotechnology Development. Agronomy
**2020**, 10, 356. [Google Scholar] [CrossRef] [Green Version] - Lai, O.; Tan, C.; Akoh, C. Palm Oil: Production, Processing, Characterization, and Uses; Elsevier Science: Amsterdam, The Netherlands, 2015. [Google Scholar]
- Corley, H.; Tinker, P. The Oil Palm; Wiley Online Library: Hoboken, NJ, USA, 2015. [Google Scholar] [CrossRef]
- Khatun, R.; Reza, M.; Moniruzzaman, M.; Yaakob, Z. Sustainable oil palm industry: The possibilities. Renew. Sustain. Energy Rev.
**2017**, 76, 608–619. [Google Scholar] [CrossRef] - Castanheira, É.G.; Acevedo, H.; Freire, F. Greenhouse gas intensity of palm oil produced in colombia addressing alternative land use change and fertilization scenarios. Appl. Energy
**2014**, 114, 958–967. [Google Scholar] [CrossRef] - Mosquera, M.; Valderrama, M.; Ruiz, E.; Lopez, D.; Castro, L. Costos de producción para el fruto de palma de aceite y el aceite de palma en 2015: Estimación en un grupo de productores colombianos. Palmas
**2017**, 38, 10–26. [Google Scholar] - Peña, A.; Bonet, I.; Lochmuller, C.; Chiclana, F.; Góngora, M. Flexible inverse adaptive fuzzy inference model to identify the evolution of operational value at risk for improving operational risk management. Appl. Soft Comput.
**2018**, 65, 614–631. [Google Scholar] [CrossRef] [Green Version] - Peña, A.; Bonet, I.; Lochmuller, C.; Patiño, H.A.; Chiclana, F.; Góngora, M. A fuzzy credibility model to estimate the Operational Value at Risk using internal and external data of risk events. Knowl.-Based Syst.
**2018**, 159, 98–109. [Google Scholar] [CrossRef] [Green Version] - Rspo Roundtable for Sustainability Palm Poil. Rspo Principles and Criteria for the Production of Sustainable Palm Oil; RSPO Roundtable for Sustainability Palm Oil: Geneva, Switzerland, 2018. [Google Scholar]
- Diaz, J. Estudio de índices de Vegetación a Partir de Imágenes Aéreas Tomadas Desde Uas/Rpas y Aplicaciones de éstos a la Agricultura de Precisión. Ph.D. Thesis, Universidad Complutense de Madrid, Madrid, Spain, 2015. [Google Scholar]
- P, A.P.; Hernández, J.A.; Toro, V.M. Computational evolutionary inverse lagrangian puff model. Environ. Model. Softw.
**2010**, 25, 1890–1893. [Google Scholar] [CrossRef] - Sadi, M.; Mahani, A. Accelerating Deep Convolutional Neural Network base on stochastic computing. Integration
**2021**, 76, 113–121. [Google Scholar] [CrossRef] - Mohammed, M.; Mwambi, H.; Mboya, I.B.; Elbashir, M.K.; Omolo, B. A stacking ensemble deep learning approach to cancer type classification based on TCGA data. Sci. Rep.
**2021**, 11, 15626. [Google Scholar] [CrossRef] - Nevruz, E.; Yildirak, K. Spatiotemporal interpolation through an extension of differential evolution algorithm for agricultural insurance claims. J. Comput. Appl. Math.
**2019**, 352, 278–292. [Google Scholar] [CrossRef] - Fitrianto, A.; Darmawan, A.; Tokimatsu, K.; Sufwandika, M. Estimating the age of oil palm trees using remote sensing technique. In Proceedings of the IOP Conference Series: Earth and Environmental Science, Banda Aceh, Indonesia, 26–27 September 2018; IOP Publishing: Bristol, UK, 2018; Volume 148, p. 012020. [Google Scholar] [CrossRef] [Green Version]
- Baseca, C.; Sendra, S.; Lloret, J.; Tomas, J. A smart decision system for digital farming. Agronomy
**2019**, 9, 216. [Google Scholar] [CrossRef] [Green Version] - Shamshiri, R.R.; Hameed, I.A.; Balasundram, S.K.; Ahmad, D.; Weltzien, C.; Yamin, M. Fundamental Research on Unmanned Aerial Vehicles to Support Precision Agriculture in Oil Palm Plantations. In Agricultural Robots-Fundamentals and Applications; IntechOpen: London, UK, 2019; Chapter 6; pp. 255–265. [Google Scholar] [CrossRef] [Green Version]
- Popovic, T.; Nedeljko, L.; Pesic, A.; Zecevic, Z.; Krstajic, B.; Djukanovic, S. Architecting an iot-enabled platform for precision agriculture and ecological monitoring: A case study. Comput. Electron. Agric.
**2017**, 140, 255–265. [Google Scholar] [CrossRef] - Pena, A.; Patino, A.; Chiclana, F.; Caraffini, F.; Gongora, M.; Gonzalez-Ruiz, J.D.; Duque-Grisales, E. Fuzzy convolutional deep-learning model to estimate the operational risk capital using multi-source risk events. Appl. Soft Comput.
**2021**, 107, 107381. [Google Scholar] [CrossRef] - Wang, Y.M.; Ostendorf, B.; Gautam, D.; Habili, N.; Pagay, V. Plant Viral Disease Detection: From Molecular Diagnosis to Optical Sensing Technology;A Multidisciplinary Review. Remote Sens.
**2022**, 14, 1542. [Google Scholar] [CrossRef] - Xue, J.; Su, B. Significant remote sensing vegetation indices: A review of developments and applications. J. Sensors
**2017**, 1353691. [Google Scholar] [CrossRef] [Green Version] - Paula Ramos, P.; Solarte, E.; Valdés, C.; Sanz, J.; Gómez, E. Características espectrales de la luz reflejada por frutos de café (coffea arabica). Rev. Soc. Colomb. Física
**2018**, 38, 822–825. [Google Scholar] - Raza, S.e.A.; Prince, G.; Clarkson, J.P.; Rajpoot, N.M. Automatic Detection of Diseased Tomato Plants Using Thermal and Stereo Visible Light Images. PLoS ONE
**2015**, 10, 1–20. [Google Scholar] [CrossRef] - Johansen, K.; Duan, Q.; Tu, Y.H.; Searle, C.; Wu, D.; Phinn, S.; Robson, A.; McCabe, M.F. Mapping the condition of macadamia tree crops using multi-spectral UAV and WorldView-3 imagery. ISPRS J. Photogramm. Remote Sens.
**2020**, 165, 28–40. [Google Scholar] [CrossRef] - Candiago, S.; Remondino, F.; De Giglio, M.; Dubbini, M.; Gattelli, M. Evaluating Multispectral Images and Vegetation Indices for Precision Farming Applications from UAV Images. Remote Sens.
**2015**, 7, 4026–4047. [Google Scholar] [CrossRef] [Green Version] - Peña, P.A.; Patiño, P.A.; Velásquez, V.J.; Góngora, M. Inteligent system to identify oil palm crop units from multispectral aerial images: Identification of multispectral patterns. In Proceedings of the 2017 12th Iberian Conference on Information Systems and Technologies (CISTI), Lisbon, Portugal, 21–24 June 2017; pp. 1–7. [Google Scholar] [CrossRef]
- Pena, A.; Patino, A.; Bonet, I.; Gongora, M. Fuzzy spatial maps to identify oil palm units: Spatial fuzzy maps. In Proceedings of the 2018 13th Iberian Conference on Information Systems and Technologies (CISTI), Caceres, Spain, 13–16 June 2018; pp. 1–6. [Google Scholar] [CrossRef]
- Khai Loong, C.; Kanniah, K.; Pohl, C.; Tan, K. A review of remote sensing applications for oil palm studies. Geo-Spat. Inf. Sci.
**2017**, 20, 184–200. [Google Scholar] [CrossRef] [Green Version] - Bhandari, A.; Kumar, A.; Singh, G. Feature extraction using normalized difference vegetation index (ndvi): A case study of jabalpur city. Procedia Technol.
**2012**, 6, 612–621. [Google Scholar] [CrossRef] [Green Version] - Torres-Sánchez, J.; López-Granados, F.; De Castro, A.; Peña-Barragán, J.M. Configuration and Specifications of an Unmanned Aerial Vehicle (UAV) for Early Site Specific Weed Management. PLoS ONE
**2013**, 8, e58210. [Google Scholar] [CrossRef] [Green Version] - Mu, X.; Song, W.; Gao, Z.; McVicar, T.R.; Donohue, R.J.; Yan, G. Fractional vegetation cover estimation by using multi-angle vegetation index. Remote Sens. Environ.
**2018**, 216, 44–56. [Google Scholar] [CrossRef] - Mohanty, S.P.; Hughes, D.P.; Salathé, M. Using Deep Learning for Image-Based Plant Disease Detection. Front. Plant Sci.
**2016**, 7, 1419. [Google Scholar] [CrossRef] [Green Version] - Sladojevic, S.; Arsenovic, M.; Anderla, A.; Culibrk, D. Stefanovic, D. Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification Computational Intelligence and Neuroscience. Comput. Intell. Neurosci.
**2016**, 2016, 11. [Google Scholar] [CrossRef] [Green Version] - Lu, Y.; Yi, S.; Zeng, N.; Liu, Y.; Zhang, Y. Identification of rice diseases using deep convolutional neural networks. Neurocomputing
**2017**, 267, 378–384. [Google Scholar] [CrossRef] - Langford, Z.L.; Kumar, J.; Hoffman, F.M. Convolutional Neural Network Approach for Mapping Arctic Vegetation Using Multi-Sensor Remote Sensing Fusion. In Proceedings of the 2017 IEEE International Conference on Data Mining Workshops (ICDMW), New Orleans, LA, USA, 18–21 November 2017; pp. 322–331. [Google Scholar] [CrossRef]
- Paoletti, M.; Haut, J.; Plaza, J.; Plaza, A. A new deep convolutional neural network for fast hyperspectral image classification. ISPRS J. Photogramm. Remote Sens.
**2018**, 145, 120–147. [Google Scholar] [CrossRef] - Park, H.G.; Yun, J.P.; Kim, M.Y.; Jeong, S.H. Multichannel Object Detection for Detecting Suspected Trees With Pine Wilt Disease Using Multispectral Drone Imagery. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.
**2021**, 14, 8350–8358. [Google Scholar] [CrossRef] - Romero, M.; Luo, Y.; Su, B.; Fuentes, S. Vineyard water status estimation using multispectral imagery from an UAV platform and machine learning algorithms for irrigation scheduling management. Comput. Electron. Agric.
**2018**, 147, 109–117. [Google Scholar] [CrossRef] - Torres, A.; Camacho, J.; Torres, J.; Cruz-Roa, A. Análisis preliminar de detección de patologías en cultivos de palma aceitera usando Redes Neuronales Convolucionales. In Proceedings of the III Congreso Internacional de Ciencias Básicas e Ingeniería—CICI 2020, Villavicencio, Colombia, 11–13 August 2020. [Google Scholar]
- Bonet, I.; Peña, A.; Lochmuller, C.; Patiño, H.A.; Chiclana, F.; Góngora, M. Applying fuzzy scenarios for the measurement of operational risk. Appl. Soft Comput.
**2021**, 112, 107785. [Google Scholar] [CrossRef] - Ghaffarian, S.; van der Voort, M.; Valente, J.; Tekinerdogan, B.; de Mey, Y. Machine learning-based farm risk management: A systematic mapping review. Comput. Electron. Agric.
**2022**, 192, 106631. [Google Scholar] [CrossRef] - Peña, A.; Bonet, I.; Lochmuller, C.; Chiclana, F.; Góngora, M. An integrated inverse adaptive neural fuzzy system with Monte-Carlo sampling method for operational risk management. Expert Syst. Appl.
**2018**, 98, 11–26. [Google Scholar] [CrossRef] - Herbold, J. Herbold, J. Crop insurance in developing economies: The insurers’ and reinsurers’ perspective. Int. J. Rural Dev.
**2010**, 4, 14–18. [Google Scholar] - Van-Gelder, J.; Sari, A.; Pacheco, P. Managing Palm Oil Risks: A Brief for Financiers; Roundtable for sustainable palm oil rspo; Profundo; Center for International Forestry Research: Bogor, Indonesia, 2017. [Google Scholar]
- Kath, J.; Mushtaq, S.; Henry, R.; Adeyinka, A.; Stone, R. Index insurance benefits agricultural producers exposed to excessive rainfall risk. Weather Clim. Extrem.
**2018**, 22, 1–9. [Google Scholar] [CrossRef] - Shirsath, P.; Vyas, S.; Aggarwal, P.; Rao, K.N. Designing weather index insurance of crops for the increased satisfaction of farmers, industry and the government. Clim. Risk Manag.
**2019**, 25, 100189. [Google Scholar] [CrossRef] - Magazzino, C.; Mele, M.; Santeramo, F.G. Using an Artificial Neural Networks Experiment to Assess the Links among Financial Development and Growth in Agriculture. Sustainability
**2021**, 13, 2828. [Google Scholar] [CrossRef] - Trenca, I.; Pece, A.M.; Mihuţ, I.S. The Assessment of Market Risk in the Context of the Current Financial Crisis. Procedia Econ. Financ.
**2015**, 32, 1391–1406. [Google Scholar] [CrossRef] [Green Version] - Basel Committee on Banking Supervision. High-Level Summary of Basel III Reforms; Bank for International Settlements: Basel, Switzerland, 2017. [Google Scholar]
- Specht, D.F. Probabilistic neural networks. Neural Netw.
**1990**, 3, 109–118. [Google Scholar] [CrossRef] - Hornik, K.; Grün, B. On conjugate families and Jeffreys priors for von Mises–Fisher distributions. J. Stat. Plan. Inference
**2013**, 143, 992–999. [Google Scholar] [CrossRef] [Green Version] - UNIPALMA de los Llanos, S.A. Guia Técnica-Polinización Asistida en Palma de Aceite; UNIPALMA de Los LLanos S.A.: Bogotá, Colombia, 2018. [Google Scholar]
- DJI-Industries, Phantom 3 Professional. 2018. Available online: https://www.dji.com/phantom-3-pro/info (accessed on 24 April 2022).
- Parrot, Parrot Sequoia-Multispectral Camera. 2018. Available online: https://www.parrot.com/uk/shop/accessories-spare-parts/other-drones/sequoia (accessed on 24 April 2022).
- Woittiez, L.S.; van Wijk, M.T.; Slingerland, M.; van Noordwijk, M.; Giller, K.E. Yield gaps in oil palm: A quantitative review of contributing factors. Eur. J. Agron.
**2017**, 83, 57–77. [Google Scholar] [CrossRef] - Magazzino, C.; Mele, M.; Sarkodie, S.A. The nexus between COVID-19 deaths, air pollution and economic growth in New York state: Evidence from Deep Machine Learning. J. Environ. Manag.
**2021**, 286, 112241. [Google Scholar] [CrossRef] [PubMed] - Nanni, A.; Tinarelli, G.; Solisio, C.; Pozzi, C. Comparison between Puff and Lagrangian Particle Dispersion Models at a Complex and Coastal Site. Atmosphere
**2022**, 13, 508. [Google Scholar] [CrossRef] - Arango, M.; Ospina, C.; Martínez, G. Uso de herramientas epidemiológicas para establecer el manejo integrado de la Marchitez letal de la palma de aceite. Palmas
**2011**, 32, 17–27. [Google Scholar] - Liu, G.; Bao, H.; Han, B. A Stacked Autoencoder-Based Deep Neural Network for Achieving Gearbox Fault Diagnosis. Math. Probl. Eng.
**2018**, 2018, 1–10. [Google Scholar] [CrossRef] [Green Version] - Peña, A.; Bonet, I.; Manzur, D.; Góngora, M.; Caraffini, F. Validation of convolutional layers in deep learning models to identify patterns in multispectral images. In Proceedings of the 2019 14th Iberian Conference on Information Systems and Technologies (CISTI), Coimbra, Portugal, 19–22 June 2019; pp. 1–6. [Google Scholar] [CrossRef]
- Charte, D.; Charte, F.; Herrera, F. Reducing Data Complexity using Autoencoders with Class-informed Loss Functions. IEEE Trans. Pattern Anal. Mach. Intell.
**2021**. [Google Scholar] [CrossRef] - Gao, B.; Pavel, L. On the Properties of the Softmax Function with Application in Game Theory and Reinforcement Learning. arXiv
**2017**, arXiv:1704.00805. [Google Scholar] - Park, O.H.; Seok, M.G. Selection of an appropriate model to predict plume dispersion in coastal areas. Atmos. Environ.
**2007**, 41, 6095–6101. [Google Scholar] [CrossRef] - Izzuddin, M.; Nisfariza, M.N.; Ezzati, B.; Idris, A.S.; Steven, M.D.; Boyd, D. Analysis of airborne hyperspectral image using vegetation indices, red edge position and continuum removal for detection of Ganoderma disease in oil palm. J. Oil Palm Res.
**2018**, 30, 416–428. [Google Scholar] - Srestasathiern, P.; Rakwatin, P. Oil Palm Tree Detection with High Resolution Multi-Spectral Satellite Imagery. Remote Sens.
**2014**, 6, 9749–9774. [Google Scholar] [CrossRef] [Green Version] - Mora, A. Cuantificación del Riesgo Operativo en Entidades Financieras en Colombia. Cuad. Adm.
**2010**, 23, 185–211. [Google Scholar] - Jantsch, L.; Solana-González, P.; Vanti, A.A. Management of Corporate Risk in Financial Institutions: An Evidence of Loss Events Derived from Operational Risk. Rev. Espac.
**2019**, 40, 21–30. Available online: https://revistaespacios.com/a19v40n06/a19v40n06p21.pdf (accessed on 24 April 2022). - Bolance, C.; Guillén, M.; Gustafsson, J.; Nielsen, J. Quantitative Operational Risk Models, 1st ed.; Chapman and Hall: London, UK, 2012. [Google Scholar] [CrossRef]

**Figure 5.**NDVI oil-palm crops affected by a phytosanitary event ($a=1$) (

**a**) healthy palm (EL, b=$-0.25$), (

**b**) apparently healthy palm (UL, b=$-0.5$), (

**c**) palm affected by LW (SL, b=$-0.75$).

**Figure 7.**NDVI-CIs classified by Substructure 1: (

**a**) NDVI-MCOP (Height: 10 m), (

**b**) NDVI non-MCOP, (

**c**) Forrest NDVI non-MCOP.

**Figure 11.**Neural connections between the IC fingerprint and the FCL layer. (

**a**) Scenario 2.1; (

**b**) Scenario 2.2; (

**c**) Scenario 2.3.

Scenario 3 | Scenario 1 | |
---|---|---|

Scenarios | Metric | Reference |

Hectares (Ha-Oil Palm Units) | 6.9 (1000) | 6.9 (1000) |

Structure of losses EL-UL-(SL) | 856-143-(1) | 744-106-(150) |

Category 1 (SL-USD) | 5580 | 4136 |

Category 2 (UL-USD) | 3053 | 5849 |

Category 3 (EL-USD) | 301 | 45,135 |

Sustainability GAP | 855 | 594 |

Scenario 3 | Scenario 1 | Scenario 2.2 | Scenario 2.1 | Scenario 2 | |
---|---|---|---|---|---|

Scenarios | Metric | Reference | Month 4 | Month 2 | Month 0 |

Hectares (Ha-Oil Palm Units) | 6.9 (1000) | 6.9 (1000) | 6.9 (1000) | 6.9 (1000) | 6.9 (1000) |

Structure of Losses EL-UL-(SL) | 856-143-(1) | 744-106-(150) | 792-130-(78) | 801-165-(34) | 840-150-(10) |

Probability Distribution | log-logistic | log-logistic | log-logistic | log-logistic | log-logistic |

**Table 3.**Behaviour of Substructure 1 in the identification and labelling of MCOPs based on reflectance bands.

NIR | REG | RED | |||||||
---|---|---|---|---|---|---|---|---|---|

Train | Val. | Gen. | Train | Val. | Gen. | Train | Val. | Gen. | |

ACC/-w | 0.6667 | 0.5333 | 0.5012 | 0.4667 | 0.3333 | 0.54126 | 0.4253 | 0.3333 | 0.5526 |

CCE | 5.3727 | 7.5218 | 8.1253 | 8.5963 | 10.7454 | 11.2356 | 8.8563 | 10.7636 | 11.2556 |

MSE | 0.4667 | 0.3333 | 0.4512 | 0.5333 | 0.6667 | 0.5443 | 0.5512 | 0.8667 | 0.9264 |

NDVI | GNDVI | NRVI | |||||||
---|---|---|---|---|---|---|---|---|---|

Train | Val. | Gen. | Train | Val. | Gen. | Train | Val. | Gen. | |

ACC-w | 0.9933 | 0.9188 | 0.9933 | 0.9733 | 0.7667 | 0.9933 | 0.4667 | 0.3333 | 0.4666 |

CCE | 0.0665 | 0.0140 | 0.0398 | 0.1030 | 0.8506 | 0.0643 | 8.9563 | 10.7454 | 8.59631 |

mse | 0.0140 | 0.2198 | 0.0056 | 0.0206 | 0.2596 | 0.0086 | 0.5333 | 0.6667 | 0.5333 |

Scenarios | Scenario 3 | LG-HDLM | Convolutional DL | Stacked DL | Scenario 1 |
---|---|---|---|---|---|

Hectares (un) | 6.9 ha.-1000 un. | 6.9 ha.-1000 un. | 6.9 ha.-1000 un. | 6.9 ha.-1000 un. | 6.9 ha.-1000 un. |

ELM-ULM-(SLM) | 856-143-(1) | 858-113-(29) | 801-165-(34) | 792-130-(78) | 744-106-(150) |

Distribution | Log-logistic | G.Extrem.V. | Gen.Pareto | G.Extrem.V. | log-logistic |

NLogL | 1629.45 | 2054.93 | 2069.75 | 2561.85 | 4206.46 |

Distribution | Log-normal | Log-logistic | Birnbaum-Saunders | Gen.Pareto | Log-normal |

NLogL | 1667.76 | 2069.35 | 2208.84 | 2591.12 | 3488.32 |

Distribution | Gen.Pareto | Gen.Pareto | Log-logistic | Log-logistic | Birnbaum-Saunders |

NLogL | 1554.43 | 2314.51 | 2314.65 | 2745.63 | 3522.90 |

IOA | 1.0000 | 0.99939 | 0.99760 | 0.99067 | 1.00000 |

VC | 50.78660 | 148.14748 | 148.45348 | 144.14446 | 148.54747 |

SK | 4.40983 | 3.46650 | 3.48849 | 3.36668 | 3.45794 |

KC | 30.04629 | 16.44628 | 16.77861 | 15.36103 | 16.25025 |

LC (USD) | 300.90 | 6748.40 | 12,788.25 | 26,684.02 | 88,775.88 |

EL (USD) | 5580.69 | 8726.14 | 4675.51 | 4622.98 | 20,869.56 |

UL (USD) | 6732.67 | 4409.92 | 10,470.26 | 7747.17 | 4795.67 |

S-GAP | 855 | 829 | 767 | 714 | 594 |

Scenario 3 | Scenario 1 | Scenario 2.2 | Scenario 2.1 | Scenario 2 | |
---|---|---|---|---|---|

Metric | Baseline | Month 4 | Month 2 | Month 0 | |

Hectares | 6.9 (1000) | 6.9 (1000) | 6.9 (1000) | 6.9 (1000) | 6.9 (1000) |

EL-UL-(SL) | 856-143-(1) | 744-106-(150) | 768-126-(106) | 798-144-(58) | 840-150-(10) |

Distribution | log-logistic | log-logistic | log-logistic | log-logistic | log-logistic |

NLogL | 1390.20 | 2314.53 | 2826.96 | 3802.20 | 4206.46 |

IOA | 1.0000 | 1.00000 | 0.89820 | 0.89436 | 0.089290 |

VC | 50.78660 | 148.54747 | 183.55119 | 212.81653 | 232.21621 |

SK | 4.40983 | 3.45794 | 2.74280 | 2.47480 | 2.41750 |

KC | 30.04629 | 16.25052 | 12.22450 | 8.36881 | 6.09664 |

ELM | 856 | 858 | 853 | 829 | 792 |

ULM | 143 | 113 | 116 | 136 | 150 |

SLM | 1 | 29 | 30 | 36 | 58 |

EL (USD) | 5580.69 | 8726.14 | 8122.91 | 7970.72 | 7268.19 |

UL (USD) | 6732.67 | 4409.92 | 4494.69 | 5155.76 | 5506.25 |

SL (USD) | 300 | 6748.40 | 6791.23 | 8193.63 | 13,554.40 |

S-GAP | 855 | 829 | 823 | 793 | 733 |

EL | UL | SL | |||
---|---|---|---|---|---|

IOA-MG-VG | IOA-MG-VG | IOA-MG-VG | Centroid $\left(xc\right)$ | Base $\left(\sigma \right)$ | |

Scenario 2 | 0.813129 | 0.850005 | 0.893388 | 0.852174 | 0.080259 |

Scenario 2.1 | 0.874696 | 0.824770 | 0.830176 | 0.843214 | 0.049926 |

Scenario 2.2 | 0.896491 | 0.899339 | 0.931133 | 0.908988 | 0.034642 |

Scenario 1 | 0.965450 | 0.993173 | 0.996007 | 0.984877 | 0.030557 |

${\sigma}_{x}$ | 0.521340 | 0.456368 | 0.201632 | 0.393113 | 0.319707 |

${\sigma}_{y}$ | 0.482561 | 0.389754 | 0.185324 | 0.352546 | 0.297237 |

Scenarios | Scenario 2.1 | Scenario 2.2 | Scenario 2.3 | ||||||
---|---|---|---|---|---|---|---|---|---|

Parameters | EL | UL | SL | EL | UL | SL | EL | UL | SL |

a | −0.83 | −1.53 | −1.38 | −0.90 | −1.77 | −1.38 | −0.82 | −1.74 | $-1.36$ |

$\alpha $ | 1.04 | 0.82 | 0.99 | 1.15 | 1.17 | 0.99 | 1.12 | 0.87 | 1.02 |

$\beta $ | 1.95 | 6.47 | 14.45 | 3.32 | 11.16 | 14.45 | 7.12 | 8.11 | 9.32 |

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**

Pena, A.; Tejada, J.C.; Gonzalez-Ruiz, J.D.; Gongora, M.
Deep Learning to Improve the Sustainability of Agricultural Crops Affected by Phytosanitary Events: A Financial-Risk Approach. *Sustainability* **2022**, *14*, 6668.
https://doi.org/10.3390/su14116668

**AMA Style**

Pena A, Tejada JC, Gonzalez-Ruiz JD, Gongora M.
Deep Learning to Improve the Sustainability of Agricultural Crops Affected by Phytosanitary Events: A Financial-Risk Approach. *Sustainability*. 2022; 14(11):6668.
https://doi.org/10.3390/su14116668

**Chicago/Turabian Style**

Pena, Alejandro, Juan C. Tejada, Juan David Gonzalez-Ruiz, and Mario Gongora.
2022. "Deep Learning to Improve the Sustainability of Agricultural Crops Affected by Phytosanitary Events: A Financial-Risk Approach" *Sustainability* 14, no. 11: 6668.
https://doi.org/10.3390/su14116668