Crop yield is a highly complex trait determined by multiple factors such as genotype, environment, and their interactions. Accurate yield prediction requires fundamental understanding of the ...functional relationship between yield and these interactive factors, and to reveal such relationship requires both comprehensive datasets and powerful algorithms. In the 2018 Syngenta Crop Challenge, Syngenta released several large datasets that recorded the genotype and yield performances of 2,267 maize hybrids planted in 2,247 locations between 2008 and 2016 and asked participants to predict the yield performance in 2017. As one of the winning teams, we designed a deep neural network (DNN) approach that took advantage of state-of-the-art modeling and solution techniques. Our model was found to have a superior prediction accuracy, with a root-mean-square-error (RMSE) being 12% of the average yield and 50% of the standard deviation for the validation dataset using predicted weather data. With perfect weather data, the RMSE would be reduced to 11% of the average yield and 46% of the standard deviation. We also performed feature selection based on the trained DNN model, which successfully decreased the dimension of the input space without significant drop in the prediction accuracy. Our computational results suggested that this model significantly outperformed other popular methods such as Lasso, shallow neural networks (SNN), and regression tree (RT). The results also revealed that environmental factors had a greater effect on the crop yield than genotype.
Maize yield has demonstrated significant variability both temporally and spatially. Numerous models have been presented to explain such variability in crop yield using data from multiple sources with ...varying temporal and spatial resolutions. Some of these models are data driven, which focus on approximating the complex relationship between explanatory variables and crop yield from massive data sets. Others are knowledge driven, which focus on integrating scientific understanding of crop growth mechanism in the modeling structure. We propose a new model that leverages the computational efficiency and prediction accuracy of data driven models and incorporates agronomic insights from knowledge driven models. Referred to as the GEM model, this model estimates three independent components of (G)enetics, (E)nvironment, and (M)anagement, the product of which is used as the predicted crop yield. The aim of this study is to produce not only accurate crop yield predictions but also insightful explanations of temporal and spatial variability with respect to weather, soil, and management variables. Computational experiments were conducted on a data set that includes maize yield, weather, soil, and management data covering 2,649 counties in the U.S. from 1980 to 2019. Results suggested that the GEM model is able to achieve a comparable prediction performance with state-of-the-art machine learning models and produce meaningful insights such as the estimated growth potential, effectiveness of management practices, and genetic progress.
Coded aperture snapshot spectral imaging (CASSI) system encodes the 3D hyperspectral image (HSI) within a single 2D compressive image and then reconstructs the underlying HSI by employing an inverse ...optimization algorithm, which equips with the distinct advantage of snapshot but usually results in low reconstruction accuracy. To improve the accuracy, existing methods attempt to design either alternative coded apertures or advanced reconstruction methods, but cannot connect these two aspects via a unified framework, which limits the accuracy improvement. In this paper, we propose a convolution neural network-based end-to-end method to boost the accuracy by jointly optimizing the coded aperture and the reconstruction method. On the one hand, based on the nature of CASSI forward model, we design a repeated pattern for the coded aperture, whose entities are learned by acting as the network weights. On the other hand, we conduct the reconstruction through simultaneously exploiting intrinsic properties within HSI-the extensive correlations across the spatial and spectral dimensions. By leveraging the power of deep learning, the coded aperture design and the image reconstruction are connected and optimized via a unified framework. Experimental results show that our method outperforms the state-of-the-art methods under both comprehensive quantitative metrics and perceptive quality.
Large-scale crop yield estimation is, in part, made possible due to the availability of remote sensing data allowing for the continuous monitoring of crops throughout their growth cycle. Having this ...information allows stakeholders the ability to make real-time decisions to maximize yield potential. Although various models exist that predict yield from remote sensing data, there currently does not exist an approach that can estimate yield for multiple crops simultaneously, and thus leads to more accurate predictions. A model that predicts the yield of multiple crops and concurrently considers the interaction between multiple crop yields. We propose a new convolutional neural network model called YieldNet which utilizes a novel deep learning framework that uses transfer learning between corn and soybean yield predictions by sharing the weights of the backbone feature extractor. Additionally, to consider the multi-target response variable, we propose a new loss function. We conduct our experiment using data from 1132 counties for corn and 1076 counties for soybean across the United States. Numerical results demonstrate that our proposed method accurately predicts corn and soybean yield from one to four months before the harvest with an MAE being 8.74% and 8.70% of the average yield, respectively, and is competitive to other state-of-the-art approaches.
Crop yield prediction is extremely challenging due to its dependence on multiple factors such as crop genotype, environmental factors, management practices, and their interactions. This paper ...presents a deep learning framework using convolutional neural networks (CNNs) and recurrent neural networks (RNNs) for crop yield prediction based on environmental data and management practices. The proposed CNN-RNN model, along with other popular methods such as random forest (RF), deep fully connected neural networks (DFNN), and LASSO, was used to forecast corn and soybean yield across the entire Corn Belt (including 13 states) in the United States for years 2016, 2017, and 2018 using historical data. The new model achieved a root-mean-square-error (RMSE) 9% and 8% of their respective average yields, substantially outperforming all other methods that were tested. The CNN-RNN has three salient features that make it a potentially useful method for other crop yield prediction studies. (1) The CNN-RNN model was designed to capture the time dependencies of environmental factors and the genetic improvement of seeds over time without having their genotype information. (2) The model demonstrated the capability to generalize the yield prediction to untested environments without significant drop in the prediction accuracy. (3) Coupled with the backpropagation method, the model could reveal the extent to which weather conditions, accuracy of weather predictions, soil conditions, and management practices were able to explain the variation in the crop yields.
To solve the low spatial and/or temporal resolution problem which the conventional hyperspectral cameras often suffer from, coded hyperspectral imaging systems have attracted more attention recently. ...Recovering a hyperspectral image (HSI) from its corresponding coded image is an ill-posed inverse problem, and learning accurate prior of HSI is essential to solve this inverse problem. In this paper, we present an effective convolutional neural network (CNN) based method for coded HSI reconstruction, which learns the deep prior from the external dataset as well as the internal information of input coded image with spatial-spectral constraint. Specifically, we first develop a CNN-based channel attention reconstruction network to effectively exploit the spatial-spectral correlation of the HSI. Then, the reconstruction network is learned by leveraging an arbitrary external hyperspectral dataset to exploit the general spatial-spectral correlation under adversarial loss. Finally, we customize the network by internal learning with spatial-spectral constraint and total variation regularization for each coded image, which can make use of the internal imaging model to learn specific prior for current desirable image and effectively avoids overfitting. Experimental results using both synthetic data and real images show that our method outperforms the state-of-the-art methods on several popular coded hyperspectral imaging systems under both comprehensive quantitative metrics and perceptive quality.
Transmission planning is typically faced with a wide range of uncertainty including growth in demand, renewable energy generation and fuel price. The restructuring of the electric power industry, the ...drive for energy independence and the push for a cleaner environment have led to additional sources of uncertainty in all aspects of power system operations and planning. The more decentralized decision-making implicates uncertainty in future generation investment and retirement of existing units. Such uncertainties are among the biggest challenges in transmission planning in power systems. However, existing approaches in the literature do not fully address this problem. In this paper, we construct a new robust transmission planning model representing generation investment and retirement uncertainty more realistically to improve the quantification and visualization of uncertainty and the impacts of environmental policies. With this model, we can manage the impacts of uncertainty in the time, the size and the location of candidate generation additions as well as the retirement of units. The corresponding algorithm we develop takes advantage of the structural characteristics of the model so as to obtain a computationally efficient solution methodology. We present an extensive numerical study on the WECC 240-bus system and illustrate the effectiveness of our approach.
Leveraging the compressive sensing (CS) theory, coded aperture snapshot spectral imaging (CASSI) provides an efficient solution to recover 3D hyperspectral data from a 2D measurement. The dual-camera ...design of CASSI, by adding an uncoded panchromatic measurement, enhances the reconstruction fidelity while maintaining the snapshot advantage. In this paper, we propose an adaptive nonlocal sparse representation (ANSR) model to boost the performance of dual-camera compressive hyperspectral imaging (DCCHI). Specifically, the CS reconstruction problem is formulated as a 3D cube based sparse representation to make full use of the nonlocal similarity in both the spatial and spectral domains. Our key observation is that, the panchromatic image, besides playing the role of direct measurement, can be further exploited to help the nonlocal similarity estimation. Therefore, we design a joint similarity metric by adaptively combining the internal similarity within the reconstructed hyperspectral image and the external similarity within the panchromatic image. In this way, the fidelity of CS reconstruction is greatly enhanced. Both simulation and hardware experimental results show significant improvement of the proposed method over the state-of-the-art.
Display omitted
► The C atom of the SiC sheet is the active adsorption site compared with the Si site. ► Adsorption of HCOH molecule could affect the electronic properties of the SiC sheet by strong ...interactions. ► The SiC sheet is expected to be a novel sensor to detect HCOH gas.
We investigated the adsorption of HCOH molecule on the SiC sheet using density functional theory (DFT) calculations. It is found that the C atom of the SiC sheet is the active adsorption site and the HCOH molecule prefers to the C atom rather than the O and H atoms close to the SiC sheet. The calculated charge-transfer, electronic density difference image and the densities of states (DOS) show that the HCOH molecule could be firmly adsorbed by the SiC sheet and the electronic properties of the SiC sheet are affected by the adsorption of HCOH molecule. The SiC sheet would be promising candidate to detect the HCOH gas.
Planting and harvest scheduling is a crucial part of crop production due to its significant impact on other factors such as balancing the capacities for harvest, yield potential, sales price, ...storage, and transportation. Corn planting and harvest scheduling is challenging because corn hybrids have different planting windows, and, subsequently, inaccurate planting and harvest scheduling can result in inconsistent and unpredictable weekly harvest quantities and logistical and productivity issues. In the 2021 Syngenta Crop Challenge, participants were given several large datasets including recorded historical daily growing degree units (GDU) of two sites and provided with planting windows, required GDUs, and harvest quantities of corn hybrids planted in these two sites, and were asked to schedule planting and harvesting dates of corn hybrids under two storage capacity cases so that facilities are not over capacity in harvesting weeks and have consistent weekly harvest quantities. The research problem includes determining the planting and harvest scheduling of corn hybrids under two storage capacity cases: (1) given the maximum storage capacity, and (2) without maximum storage capacity to determine the lowest storage capacity for each site. To help improve corn planting and harvest scheduling, we propose two mixed-integer linear programming (MILP) models and a heuristic algorithm to solve this problem for both storage capacity cases. Daily GDUs are required for planting and harvest scheduling, but they are unknown at the beginning of the growing season. As such, we use recurrent neural networks to predict the weekly GDUs of 70 weeks and consider this as the predicted GDU scenario to solve this problem. In addition, we solve this problem considering all given 10 historical GDU scenarios from 2010 to 2019 together for both storage capacity cases to include historical GDUs directly to our model rather than using predicted GDUs. Our extensive computational experiments and results demonstrate the effectiveness of our proposed methods, which can provide optimal planting and harvest scheduling considering deterministic GDU scenario and uncertainties in historical GDU scenarios for both storage capacity cases to provide consistent weekly harvest quantities that are below the maximum capacity.