=Paper=
{{Paper
|id=Vol-2846/paper10
|storemode=property
|title=Deep Learning Approaches for Forecasting Strawberry Yields and Prices Using Satellite Images and Station-Based Soil Parameters
|pdfUrl=https://ceur-ws.org/Vol-2846/paper10.pdf
|volume=Vol-2846
|authors=Mohita Chaudhary,Mohamed Sadok Gastli,Lobna Nassar,Fakhri Karray
|dblpUrl=https://dblp.org/rec/conf/aaaiss/ChaudharyGNK21
}}
==Deep Learning Approaches for Forecasting Strawberry Yields and Prices Using Satellite Images and Station-Based Soil Parameters==
https://ceur-ws.org/Vol-2846/paper10.pdf
Deep Learning Approaches for Forecasting
Strawberry Yields and Prices Using Satellite Images
and Station-Based Soil Parameters
Mohita Chaudharya , Mohamed Sadok Gastlia , Lobna Nassara and Fakhri Karraya
a
Department of Electrical and Computer Engineering, University of Waterloo, Ontario, Canada
Abstract
Computational tools for forecasting yields and prices for fresh produce have been based on traditional
machine learning approaches or time series modeling. We propose here an alternate approach based
on deep learning algorithms for forecasting strawberry yields and prices in Santa Barbara county, Cali-
fornia. Building the proposed forecasting model comprises three stages: first, the station-based ensem-
ble model (ATT-CNN-LSTM-SeriesNet_Ens) with its compound deep learning components, SeriesNet
with Gated Recurrent Unit (GRU) and Convolutional Neural Network LSTM with Attention layer (Att-
CNN-LSTM), are trained and tested using the station-based soil temperature and moisture data of Santa
Barbara as input and the corresponding strawberry yields or prices as output. Secondly, the remote
sensing ensemble model (SIM_CNN-LSTM_Ens), which is an ensemble model of Convolutional Neural
Network LSTM (CNN-LSTM) models, is trained and tested using satellite images of the same county as
input mapped to the same yields and prices as output. These two ensembles forecast strawberry yields
and prices with minimal forecasting errors and highest model correlation for five weeks ahead forecasts.
Finally, the forecasts of these two models are ensembled to have a final forecasted value for yields and
prices by introducing a voting ensemble. Based on an aggregated performance measure (AGM), it is
found that this voting ensemble not only enhances the forecasting performance by 5% compared to its
best performing component model but also outperforms the Deep Learning (DL) ensemble model found
in literature by 33% for forecasting yields and 21% for forecasting prices.
Keywords
Deep Learning, Satellite Images, Price, Yield, Forecasting, Fresh Produce, Attention, Series-Net
1. Introduction
In Fresh produce Supply Chain Management (FSCM), a crucial part of the procurement pro-
cess is to find a model which helps in precisely predicting the farmersβ prices. These prices
are highly affected by the yields hence the availability of accurate yields values to train the
forecasting model is crucial [1].
In A. Martin, K. Hinkelmann, H.-G. Fill, A. Gerber, D. Lenat, R. Stolle, F. van Harmelen (Eds.), Proceedings of the AAAI
2021 Spring Symposium on Combining Machine Learning and Knowledge Engineering (AAAI-MAKE 2021) - Stanford
University, Palo Alto, California, USA, March 22-24, 2021.
" m38chaud@uwaterloo.ca (M. Chaudhary); ms2gastli@uwaterloo.ca (M.S. Gastli); lnassar@uwaterloo.ca (L.
Nassar); karray@uwaterloo.ca (F. Karray)
0000-0002-1195-6927 (M. Chaudhary); 0000-0003-2970-1153 (M.S. Gastli); 0000-0002-9590-8403 (L. Nassar);
0000-0002-4217-1372 (F. Karray)
Β© 2021 Copyright for this paper by its authors.
Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
CEUR
Workshop
Proceedings
http://ceur-ws.org
ISSN 1613-0073 CEUR Workshop Proceedings (CEUR-WS.org)
This study focuses on strawberries as fresh produce, whose yield depends on various param-
eters related to weather, soil, synthetic factors, irrigation, and others. These factors are quite
uncertain therefore the forecasting of strawberry yields and prices is a challenging task. More-
over, from a humanitarian point of view, the United Nations World Food Programme has re-
ported that around 821 million people around the world suffer from hunger [2], and that num-
ber has been growing drastically since the start of the COVID-19 pandemic. This is part of
the reason why the United Nations have included ending hunger and the betterment of food
security as part of their main goals in their 2030 Agenda for Sustainable Development [3]. A
key aspect to overcome these issues and a significant challenge facing food security is the abil-
ity to reliably estimate crop yields using forecasting models; the main objective of this work.
It should be noted that such forecasting models for strawberries can be applied on numerous
similar fresh produces for better yields estimates to sustain food security.
The acquisition of data can be very expensive with limited availability. California is chosen
since the data for its strawberry yields, prices, and soil parameters can be acquired from various
publicly available online sources. Due to the frequent absence of localized data, using remote
sensing data such as satellite images is important since they can cover larger geographic areas.
Santa Maria, which lies within Santa Barbara county, is primarily considered in this work
because it is one of the largest stations for strawberry produce in California; it is considered the
leading state producer for strawberries [4]. The yields and prices are predicted by manipulating
historical input data to extract features that can capture as many yields and prices trends as
possible. Currently used forecasting tools for fresh produce have limited performance since
they do not consider an extensive set of influential factors affecting yields and prices. They
are also incapable of capturing the complex patterns in big data sources of prices transactions
which provide valuable information on the underlying processes affecting fresh produce prices
and quantities; this became feasible by the advent of the state-of-the-art machine learning and
DL techniques.
The scope of this work is forecasting both strawberry yields and prices using input features
related to soil parameters. The yields and prices values are forecasted 5 weeks ahead. It is
found that the past 20 weeks values of the soil parameters affect the yields and hence this is
the lag considered to forecast the yields and prices. An aggregated measure is used to gauge
the performance of the forecasting models, which are compared to a simple LSTM model and a
compound DL ensemble model proposed in [5]. The voting regressor ensemble of ATT-CNN-
LSTM-SeriesNet_Ens and SIM_CNN-LSTM_Ens models outperforms its compound component
models as well as simple DL models such as LSTM. Moreover, it enhances the performance of
the compound DL ensemble model described in [5] by up to 33%.
Section 2 highlights literature review and previous work done in this area, it also summarizes
major findings and limitations. The details of the assembled forecasting compound DL models
are provided in Section 3. The datasets, data preprocessing, and results of the conducted ex-
periments are presented and analyzed in Section 4. Finally, the drawn conclusion along with
future work are found in Section 5.
2. Literature Review
Various methods are used for yields prediction like Artificial Neural Networks [6, 7], K-Nearest
Neighbors [8, 4] and Simple Long Short Term Memory Networks (LSTM) [9]. The weather
parameters are used as input parameters to predict the yields in [10]; while in [11, 5], the
corresponding prices to strawberry yields are predicted using various DL compound models
like ConvLSTM, CNN-LSTM, CNN-LSTM-GRU with attention along with DL ensemble models.
Adding a self-attention layer improves the yield prediction results to quite an extent. Moreover,
the DL models are recommended over nondeep ML and non-ML models for forecasting. In
[12], various machine learning and DL imputation techniques for missing values in datasets
are discussed. In [9], the weather parameters, soil moisture dynamic data and soil quality static
data across various counties in Iowa, USA are used as input to forecast the yearly corn yields
using a basic LSTM network. The static parameters remain constant over years for a specific
region and they are useful only when different regions are considered. The work presented
here considers the dynamic parameters solely as input and ignores the static ones since only the
Santa Maria county is considered for forecasting yields and prices. In [13], counter-propagation
artificial neural networks (CP-ANNs) and Supervised Kohonen Networks (SKNs) are used to
predict the wheat yields using a found set of influential soil parameters.
As for the use of remote sensing in crop yields forecasting, existing approaches are inves-
tigated. Three recent methods and applications are presented in [14, 15, 16]. Their general
framework involves using a preprocessed collection of satellite-based data to train neural net-
works for yields prediction. The first approach is conducted in [14] by J. You et al., where they
use satellite images that are publicly available to predict annual soybean yields for specific
counties in the USA. The images used comprise 7 bands of surface reflectance and 2 bands of
temperature. The authors preprocessed these images into histograms due to their large size,
then fed them into several prediction models for comparison. The models used are Convolu-
tional Neural Network (CNN) and LSTM. Their results indicate that the CNN models are better
than LSTM in predicting yields. However, it should be noted that this approach investigates
yearly yields and not daily forecasts. This is further investigated by J. Phongpreecha in [15],
who considers moisture in addition to surface reflectance and temperature satellite images to
predict annual corn yields. He also implements dimensionality reduction to histograms as de-
scribed by [14]. The investigated models are a Custom CNN-LSTM, a Separable CNN-LSTM,
a CNN-LSTM, a 3D-CNN, and a CNN-LSTM-3D CNN network. The ConvLSTM is found to be
the best performing model in forecasting annual corn yields. A similar approach is conducted
in [16] where the authors investigate such application in southern Brazil on annual soybean
yields. Their approach considers satellite images in addition to precipitation data obtained
from weather stations. Three models are tested, namely multivariate OLS linear regression,
random forest, and LSTM where, LSTM outperforms the other two models in forecasting.
From the literature review, it is evident that neural networks, specifically CNN, LSTM, and
combinations of both, are best suited for the forecasting application. The limitations of the
presented approaches are either considering data collected from localized stations for forecast-
ing, such data is not readily available for all croplands on earth, or giving annual predictions of
yields using weekly satellite images. Thus, daily predictions are essential with more complex
deep leaning models for higher performance.
Figure 1: Architecture of CNN-LSTM with Attention
Furthermore, the satellite images should be used alongside the stationary data to overcome the
frequent problem of data scarcity.
3. Proposed Models and Methodology
Two models are used for forecasting which are then fed into an ensemble to combine their
outputs into a final forecasted value. The first model uses station-based soil data as input
while the other relies on soil data captured by satellite images instead. Compound DL models
are proved to perform better than simple DL and nondeep ML models as described in [5]. The
simple DL model, LSTM, and the ensemble model described in [5] are compared to the proposed
model.
3.1. The Station-based Model (ATT-CNN-LSTM-SeriesNet_Ens)
This model uses the station-based soil data to forecast the strawberry yields and prices. After
preprocessing, the data is fed into two compound DL models namely Att-CNN-LSTM and
SeriesNet with GRU. The forecasted output values of each of these two models are then fed
as input into a voting ensemble which outputs the final forecasted yields or prices.
3.1.1. Att-CNN-LSTM
The self-attention layer helps in focusing on the essential details in the input data. In the
proposed model, the attention layer uses additive attention and the sigmoid activation function.
Figure 1 shows the architecture of the Att-CNN-LSTM compound model. The self-attention is a
mechanism which deals with the different positions of a single sequence and then computes the
representation of that sequence. The layer is applied atop every unit of the sequence; additive
attention is used. The attention function helps in mapping a query and a set of key-value pairs
to an output. Here, the keys, output, values and queries are all considered as vectors [17].
The Additive Attention works by using a feed forward network to calculate the compatibility
function [18]. The equations are described in (1), (2), (3), and (4).
βπ‘,π‘ β² = tanh (π₯π‘π ππ‘ + π₯π‘πβ² ππ₯ + ππ‘ ) (1)
ππ‘,π‘ β² = π(ππ βπ‘,π‘ β² + ππ ) (2)
ππ‘ = softmax(ππ‘ ) (3)
ππ‘ = β ππ‘,π‘ β² π₯π‘ β² (4)
π‘β²
Figure 2: Architecture of SeriesNet with GRU
where π is the element-wise sigmoid function and ππ₯ and ππ‘ are the weight matrices corre-
sponding to π₯π‘π and π₯π‘πβ² . ππ is the weight matrix corresponding to the non-linear combination
of ππ₯ and ππ‘ , while ππ‘ and ππ are the bias vectors [17]. Equation (4) shows how the atten-
tion value ππ‘ is computed. The probability distribution ππ‘ and compatibility score ππ‘,π‘ β² must be
calculated first to find the value of attention. The compatibility score is calculated using the
hidden representation βπ‘,π‘ β² of π₯π‘π and π₯π‘πβ² . The use of Attention layer contributes significantly to
performance by reducing the forecasting error of the DL models. The improvement in perfor-
mance is evident in the results reported by [17, 18, 19, 20] in domains such as natural language
processing, fresh produce related predictions and healthcare questionnaires.
Stacking CNNs and LSTMs together helps in utilizing the strength of each of these models
[21, 18]. The CNNs help in extracting the spatial features whereas the LSTMs help in ex-
tracting the temporal features and using their combination highly improves the forecasting
performance. The attention layer is added to the CNN-LSTM compound network to improve
its performance.
3.1.2. SeriesNet with GRU
In this model, the GRU is used alongside the dilated causal convolution. The GRU network is a
two-layer network with attention module in between. The output at the end is flattened and fed
into a single neuron dense layer. The number of layers and neurons alter as per the application.
The architecture of the model is illustrated in Figure 2. Gated Recurrent Unit (GRU) [22] is a
newer version of RNNs and is quite similar to LSTMs [23]. GRUs use hidden states rather than
using the cell state or memory to transfer the information.
Figure 3: CNN-LSTM architecture for yields Figure 4: CNN-LSTM architecture for prices
forecasting using satellite images forecasting using satellite images
They have two gates, a reset gate, and an update gate. The update gate acts similarly to the
forget gate and input gates of LSTM. The reset gate, on the contrary, is used to decide how much
past information has to be forgotten. GRUs are faster than LSTMs since they have fewer tensor
operations. Both LSTMs and GRUs are designed to overcome the short-term memory issues
faced by RNNs. Since RNNs face vanishing or exploding gradient issues, GRUs are introduced
to mitigate those issues. The structure is similar to those of LSTMs and consists of gates that
ensure that the issue of gradient is not encountered.
The traditional time series forecasting models are unable to effectively extract essential data
features; thus the authors in [24] came up with a novel forecasting architecture called Series-
Net. The SeriesNet consists of two networks, an LSTM network and a dilated causal convo-
lution network. The dilated convolution handles the loss of resolution or coverage due to the
down-sampling operation in image semantic segmentation [25]. It uses dilated convolutions
to systematically aggregate multi-scale contextual information and improve the accuracy of
image recognition. The causal convolution ensures that the convolution kernel of CNN can
perform convolution operations exactly in time sequence [26], and that the convolution kernel
only reads the current and historical information. The LSTM network aims to learn holistic
features and to reduce dimensionality of multi-conditional data. The combined results of the
networks help the models to learn multi-range and multilevel features from time series data,
hence it has higher predictive accuracy compared to other models. The SeriesNet with GRU
model uses residual learning as well as batch normalization to improve generalization.
3.2. The Remote Sensing Ensemble Model (SIM_CNN-LSTM_Ens)
This model is an ensemble of CNN-LSTM. It incorporates the capabilities of both CNN and
LSTM by treating them as layers. The architecture for the CNN-LSTM model used for yields
forecasting is presented in Figure 3, which differs from the prices forecasting model. It should
also be noted that the models are fine tuned through trial and error of multiple configurations.
As for the CNN-LSTM prices forecasting model, its architecture is presented in Figure 4. The
preprocessing is implemented using the Geospatial Data Abstraction Library (GDAL) [27] in
Python to import the images into a processable format. After preprocessing, the features are
fed into the designed models. These models are implemented uisng Pythonβs Tensoflow Keras
library [28] due to its user-friendliness.
Figure 5: Block diagram of the proposed ensemble model
3.3. Ensemble of ATT-CNN-LSTM-SeriesNet_Ens and SIM_CNN-LSTM_Ens
The previous approaches extract different features from their data, therefore averaging their
forecasted outputs could potentially lead to a better overall forecast. Hence, a voting ensem-
ble is required to achieve this averaging. Figure 5 illustrates the overall architecture of the
final proposed model. The outputs of both compound models are combined by the averaging
ensemble to obtain the final forecast.
3.4. Evaluation Metrics
The metrics used for analysis are the Mean Absolute Error (MAE), the Root Mean-Squared Error
(RMSE), R-Squared coefficient (π
2 ), and the Aggregated Measure (AGM). The unit in which
MAE is measured is pounds/acre for yield and US dollars for price. The AGM is a measure
composed of all the previously mentioned metrics, whose purpose is to attempt to incorporate
the information captured by all three metrics into one metric to simplify the process of deciding
the best performing model [11, 29]. The measure is negatively-oriented, meaning lower scores
indicate better performance. It is mathematically defined in (5).
π
πππΈ + ππ΄πΈ
π΄πΊπ = Γ (1 β π
2 ) (5)
2
4. Datasets, Experiments and Analysis
4.1. Datasets and Preprocessing
4.1.1. Station-based Data
There are various parameters related to the soil affecting the yields and prices of fresh produce
namely: soil moisture, soil temperature, solar radiation, surface temperature, PDSI (Palmer
Drought Severity Index) [30, 31],... etc. Choosing the most influential parameters is a major
challenge due to the high correlation amongst those parameters. Hence, the Random Forest
feature selection method in Python with scikit-learn is used and the soil moisture and tem-
perature are selected accordingly as the most important parameters. Moreover, soil moisture
and temperature are the two soil parameters that can be obtained from satellite images as well.
Figure 6:
Image samples from the temperature
bands (left) and the moisture bands (right) Figure 7: Input sample histogram structure
The station-based soil data is downloaded from the National Oceanic and Atmospheric Ad-
ministration website [32]. The data for strawberry yields and prices are downloaded from the
California Strawberry Commission website [33]. A lag of the past 20 weeks, i.e. 140 days, of
soil parameters values is found to affect the yields forecasting and prices values 5 weeks ahead.
Two daily parameters are considered, soil temperature and moisture, hence the total number
of input parameters adds up to 280 (2 parameters x 140 days). After normalizing the data, the
Principal Component Analysis (PCA) [34] is applied on the 280 parameters and it is found that
the first 36 parameters gave the maximum proportion of variance therefore are chosen to train
and test the forecasting model along with the corresponding yields or prices output. The total
number of available samples is 2812 (from year 2011 to 2019) out of which 80% are used for
training and 20% for testing.
4.1.2. Remote Sensing Data
The remote sensing data contains two sets of satellite images; one for surface temperature
data and the other for moisture data. The images in the temperature dataset, obtained from
[35], are taken daily, whereas those in the moisture dataset, obtained from [36], are taken
every 3 days. Therefore, each moisture image is duplicated twice, once for the day before the
original image and once for the day after, in order to have daily moisture values along with the
daily temperature. This approach is an approximation of the missing days based on the closest
known data to those days. Samples of the original images obtained from the datasets for Santa
Barbara county are presented in Figure 6. The moisture bands are for the mainland moisture
levels, which is why the data is not available for the islands and coastal areas. In addition, a
land cover mask is applied to all images, obtained from the MODIS database [35]. The mask
maintains the pixel values of the image parts of interest, while setting pixels not within the
mask to a zero value, to ensure that the model only trains on pixel values that correspond to
crop lands hence minimizing the number of pixels processed. The total number of samples is
2977 (from year 2011 to 2019) out of which 80% are used for training and 20% for testing.
As shown in [14], the images are too large to be fed directly into the model. Thus, dimen-
sionality reduction is applied by converting them into histograms of pixel frequency counts.
Figure 8: Forecasted vs. true yields values Figure 9: Forecasted vs. true prices values
This reduction is based on the assumption of permutation invariance, meaning that shuffling
the pixels has no effect on the information retained in the image. The histograms are then
normalized based on their pixel values. Surface reflectance bands used in [14] and [15] are
omitted due to their negligible improvement to the prediction performance for the considered
county and fresh produce. The number of bins, π, is set to be 32; as it is a reasonable spread
of pixel counts as found in [14]. Moreover, the range of pixel values for each band is chosen
to maximize the spread of the pixels count distribution. The structure is visualized in Figure 7;
where the three axes represent the three dimensions of the histogram. Before being fed to the
models, the bins and bands dimensions are flattened into a single dimension to fit the models.
4.2. Experiments and Analysis
The block diagram in Figure 5 depicts the proposed final model, which has a voting ensemble
which averages the forecasted yields or prices resulting from the two proposed DL compound
ensembles described in Section 3.1 and Section 3.2. The main idea behind this averaging is that
the final forecast should pick the trends forecasted by both of the component models.
For yield forecasting, Figure 8 shows the true yields versus the yields forecasted by ATT-
CNN-LSTM-SeriesNet_Ens, SIM_CNN-LSTM_Ens, and their averaging ensemble. The figure
shows that the voting ensemble successfully follows the general trend of the true values despite
its inability to describe the sharp fluctuations. Table 1 presents different metrics scores of the
forecasted values for the different models. Although SIM_CNN-LSTM_Ens outperforms ATT-
CNN-LSTM-SeriesNet_Ens in AGM, the averaging ensemble outperforms both of its weaker
component models with its lowest AGM. This indicates that there is some information obtained
by the latter that enhances the performance compared to the individual models. Based on AGM,
the voting ensemble enhances the forecasting performance over that of the DL ensemble model
in [5] by 33% and that of the simple LSTM DL by 56%.
For prices forecasting, Figure 9 depicts the true prices versus the prices forecasted by ATT-
CNN-LSTM-SeriesNet_Ens, SIM_CNN-LSTM_Ens, and the averaging ensemble of both. Table
2 presents different performance metrics scores for the tested models. Although ATT-CNN-
LSTM-SeriesNet_Ens outperforms SIM_CNN-LSTM_Ens with a noticeable AGM difference,
the voting ensemble outperforms both of these compound components with its lowest AGM.
The voting ensemble persists to be the highest performing compared to the LSTM model, 53%
improvement, and to the ensemble model in [5], 21% improvement in AGM.
Table 1
Results for using LSTM, SIM_CNN-LSTM_Ens, and ATT-CNN-LSTM-SeriesNet_Ens to forecast yield
Score LSTM Ensemble in [5] SIM_CNN-LSTM_Ens ATT-CNN-LSTM-SeriesNet_Ens Voting Ensemble
MAE 53.1 42.5 39.1 40.7 37.0
RMSE 70.8 62.2 55.2 58.8 54.6
π
2 0.780 0.83 0.866 0.848 0.869
AGM 13.6 9.0 6.3 7.5 6.0
Table 2
Results for using LSTM, SIM_CNN-LSTM_Ens, and ATT-CNN-LSTM-SeriesNet_Ens to forecast price
Score LSTM Ensemble in [5] SIM_CNN-LSTM_Ens ATT-CNN-LSTM-SeriesNet_Ens Voting Ensemble
MAE 0.268 0.21 0.227 0.214 0.208
RMSE 0.341 0.27 0.292 0.263 0.264
π
2 0.609 0.72 0.712 0.766 0.764
AGM 0.119 0.07 0.0748 0.0557 0.0555
5. Conclusion and Future Work
This paper explores the application of multiple DL models in forecasting strawberry yields and
prices. Station-based data is used to train the ATT-CNN-LSTM-SeriesNet_Ens, while remote
sensing-based data is used to train the SIM_CNN-LSTM_Ens for forecasting. It is found that
the SIM_CNN-LSTM_Ens model does better at yields forecasting while the ATT-CNN-LSTM-
SeriesNet_Ens model is better at prices forecasting. The voting ensemble of these models out-
performs its individual components since each component provides a different forecasting be-
havior. Moreover, it further proves to perform better by up to 33% compared to the most recent
DL ensemble forecasting model. An acknowledged limitation is the restricted ability of the de-
ployed models to capture steep fluctuations in yields and prices, making them not predictable
with the available tools. Moreover, having an ensemble of various compound DL models is
computationally expensive. Potential future work is needed to further improve the ability of
the models to capture steep fluctuations in both yields and prices. Generalization of the models
application to other fresh produces is also required; this is achieved through transfer learning
to forecast yields and prices of FPs similar to strawberries efficiently with minimal retraining.
Acknowledgments
The authors would like to acknowledge the financial support provided by Loblaws corporation,
NSERC CRD program and Mitacs.
References
[1] R. Waldick, L. Bizikova, D. White, K. Lindsay, An integrated decision-support process for
adaptation planning: climate change as impetus for scenario planning in an agricultural
region of canada, Regional Environmental Change 17 (2017) 187β200.
[2] UN World Food Programme, 2019 - hunger map, 2019. URL: https://www.wfp.org/
publications/2019-hunger-map, accessed 27.11.2020.
[3] United Nations General Assembly, Transforming our World: The 2030 Agenda for
Sustainable Development, 2015. URL: https://sustainabledevelopment.un.org/post2015/
transformingourworld/publication, accessed 27.11.2020.
[4] T. B. Pathak, S. K. Dara, A. Biscaro, Evaluating correlations and development of meteo-
rology based yield forecasting model for strawberry, Advances in Meteorology (2016).
[5] I. Okwuchi, Machine Learning based Models for Fresh Produce Yield and Price Forecasting
for Strawberry Fruit, Masterβs thesis, University of Waterloo, 2020.
[6] F. O. Karray, C. W. De Silva, Soft computing and intelligent systems design: theory, tools,
and applications, Pearson Education, 2004.
[7] P. Doganis, A. Alexandridis, P. Patrinos, H. Sarimveis, Time series sales forecasting for
short shelf-life food products based on artificial neural networks and evolutionary com-
puting, Journal of Food Engineering 75 (2006) 196β204.
[8] M. L. Maskey, T. B. Pathak, S. K. Dara, Weather based strawberry yield forecasts at field
scale using statistical and machine learning models, Atmosphere 10 (2019) 378.
[9] Z. Jiang, C. Liu, N. P. Hendricks, B. Ganapathysubramanian, D. J. Hayes, S. Sarkar, Predict-
ing county level corn yields using deep long short term memory models, arXiv preprint
arXiv:1805.12044 (2018).
[10] M. Kaul, R. L. Hill, C. Walthall, Artificial neural networks for corn and soybean yield
prediction, Agricultural Systems 85 (2005) 1β18.
[11] L. Nassar, I. E. Okwuchi, M. Saad, F. Karray, K. Ponnambalam, P. Agrawal, Prediction
of strawberry yield and farm price utilizing deep learning, in: 2020 International Joint
Conference on Neural Networks (IJCNN), IEEE, 2020, pp. 1β7.
[12] M. Saad, M. Chaudhary, F. Karray, V. Gaudet, Machine learning based approaches for
imputation in time series data and their impact on forecasting, in: 2020 IEEE International
Conference on Systems, Man, and Cybernetics (SMC), IEEE, 2020, pp. 2621β2627.
[13] X. E. Pantazi, D. Moshou, T. Alexandridis, R. L. Whetton, A. M. Mouazen, Wheat yield
prediction using machine learning and advanced sensing techniques, Computers and
Electronics in Agriculture 121 (2016) 57β65.
[14] J. You, X. Li, M. Low, D. Lobell, S. Ermon, Deep gaussian process for crop yield prediction
based on remote sensing data, in: Thirty-First AAAI Conference on Artificial Intelligence,
2017, p. 4559β4565.
[15] J. Phongpreecha, Early corn yields prediction using satel-
lite images, 2018. URL: https://towardsdatascience.com/
early-corn-yields-prediction-using-satellite-images-dcf49b24efab, accessed 27.11.2020.
[16] R. A. Schwalbert, T. Amado, G. Corassa, L. P. Pott, P. Prasad, I. A. Ciampitti, Satellite-based
soybean yield forecast: Integrating machine learning and weather data for improving crop
yield prediction in southern Brazil, Agricultural & Forest Meteorology 284 (2020) 107886.
[17] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ε. Kaiser, I. Polo-
sukhin, Attention is all you need, in: Advances in neural information processing systems,
2017, pp. 5998β6008.
[18] Y. Zhang, J. Zheng, Y. Jiang, G. Huang, R. Chen, A text sentiment classification modeling
method based on coordinated cnn-lstm-attention model, Chinese Journal of Electronics
28 (2019) 120β126.
[19] S. De Alwis, Y. Zhang, M. Na, G. Li, Duo attention with deep learning on tomato yield
prediction and factor interpretation, in: Pacific Rim International Conference on Artificial
Intelligence, Springer, 2019, pp. 704β715.
[20] R. Cai, B. Zhu, L. Ji, T. Hao, J. Yan, W. Liu, An cnn-lstm attention approach to under-
standing user query intent from online health communities, in: 2017 IEEE International
Conference on Data Mining Workshops (ICDMW), IEEE, 2017, pp. 430β437.
[21] L. Zheng, W. Xue, F. Chen, P. Guo, J. Chen, B. Chen, H. Gao, A fault prediction of equip-
ment based on cnn-lstm network, in: 2019 IEEE International Conference on Energy
Internet (ICEI), IEEE, 2019, pp. 537β541.
[22] R. Dey, F. M. Salemt, Gate-variants of gated recurrent unit (gru) neural networks, in: 2017
IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS), IEEE,
2017, pp. 1597β1600.
[23] R. Fu, Z. Zhang, L. Li, Using lstm and gru neural network methods for traffic flow pre-
diction, in: 2016 31st Youth Academic Annual Conference of Chinese Association of
Automation (YAC), IEEE, 2016, pp. 324β328.
[24] Z. Shen, Y. Zhang, J. Lu, J. Xu, G. Xiao, SeriesNet: A Generative Time Series Forecasting
Model, in: International Joint Conference on Neural Networks (IJCNN), IEEE, 2018.
[25] F. Yu, V. Koltun, Multi-scale context aggregation by dilated convolutions, arXiv preprint
arXiv:1511.07122 (2015).
[26] A. v. d. Oord, S. Dieleman, H. Zen, K. Simonyan, O. Vinyals, A. Graves, N. Kalchbrenner,
A. Senior, K. Kavukcuoglu, Wavenet: A generative model for raw audio, arXiv preprint
arXiv:1609.03499 (2016).
[27] F. Warmerdam, et al., GDAL, n.d. URL: https://gdal.org/, accessed 27.01.2021.
[28] F. Chollet, et al., Keras, https://keras.io, 2015.
[29] L. Nassar, M. Saad, I. E. Okwuchi, M. Chaudhary, F. Karray, K. Ponnambalam, Imputation
impact on strawberry yield and farm price prediction using deep learning, in: IEEE Inter-
national Conference on Systems, Man, and Cybernetics (SMC), IEEE, 2020, pp. 3599β3605.
[30] Details on the Soil Parameters, n.d. URL: https://www1.ncdc.noaa.gov/pub/data/uscrn/
products/hourly02/README.txt, accessed 27.11.2020.
[31] Palmer Drought Severity Index and Palmer Z-Index, n.d. URL: http://www.
worldwindsinc.com/palmer.htm, accessed 27.11.2020.
[32] National Oceanic and Atmospheric Administrations, n.d. URL: https://www.noaa.gov/,
accessed 27.11.2020.
[33] The California Strawberry Commission website, n.d. URL: https://www.calstrawberry.
com/en-us/, accessed 27.11.2020.
[34] H. Abdi, L. J. Williams, Principal component analysis, Wiley interdisciplinary reviews:
computational statistics 2 (2010) 433β459.
[35] LP DAAC MODIS, n.d. URL: http://lpdaac.usgs.gov/, accessed 27.11.2020.
[36] NASA-USDA global soil moisture data, n.d. URL: https://earth.gsfc.nasa.gov/hydro/data/
nasa-usda-global-soil-moisture-data, accessed 27.11.2020.