Search

Deep learning methods have been widely used in applications of yield estimation using remote sensing data. However, they still face some challenges in terms of accuracy due to their inability to fully utilize the spatiotemporal information of remote sensing data. In response to this problem, a winter wheat yield estimation method based on ensemble deep learning and Gaussian process (GP) was proposed. First, the long-short term memory (LSTM) network and convolutional neural network (CNN) were constructed to explore deep spatiotemporal features from Sentinel-1A time-series images. Then, a GP component was applied for fusion of intraimage deep spatiotemporal features and inter-sample spatial consistency features. Finally, the yield estimation results were obtained. The experimental results showed that the proposed method had higher accuracy than those compared models, with a coefficient of determination (${R^2}$ R 2 ) of 0.698, a root mean square error (RMSE) of 477.045 kg/ha and a mean absolute error (MAE) of 404.377 kg/ha, demonstrating the application potential of the proposed method in crop yield estimation applications. [ABSTRACT FROM AUTHOR]

As an emerging field, the G-Itô stochastic calculus plays an important role in describing the model uncertainty. Many interesting works have been done on stochastic differential equations driven by G-Brownian motion (G-SDEs). Among the theories and applications of G-SDEs, the stability is the vital important one. In this paper, we investigate the stabilisation for G-SDEs based on G-Lyapunov function and aperiodically adaptive intermittent controller. As an application, the sufficient conditions are established for the stabilisation of stochastic Cohen–Grossberg neural networks driven by G-Brownian motion (G-SCGNNs). Finally, an example is provided to illustrate the obtained results. [ABSTRACT FROM AUTHOR]

The thermodynamical process of latent heat flux is added to an analogical delayed oscillator model of the El Nino-Southern Oscillation (ENSO) that mainly considers equatorial ocean dynamics and produces regular, non-phase-locked oscillations. Latent heat flux affects the model sea surface temperature (SST) variations by a positive feedback between the surface wind speed and SST operating through evaporation, which is called the wind speed-evaporation-SST feedback. The wind speed-evaporation-SST feedback in which the atmosphere interacts thermodynamically with the ocean through surface heat flux differs from the conventional zonal wind stress-SST feedback in which the atmosphere interacts dynamically with the ocean through momentum flux. The combination of equatorial ocean dynamics and thermodynamics produces relatively more realistic model oscillations. When the annual cycle amplitude of the zonal wind in the wind speed-evaporation-SST feedback is gradually increased, the model solution undergoes a transition from periodic to chaotic and then to periodic oscillations for some ranges of the parameters, whereas for other ranges of the parameters the transition goes from periodic to quasiperiodic and then to periodic oscillations. The route to chaos is the intermittency route. Along with such irregularity, the nonlinear interactions between the annual and interannual cycles operating through the wind speed-evaporation-SST feedback also produce a phase-locking of ENSO to the seasonal cycle. The model ENSO onset and peak occur in the boreal winter and spring, respectively, consistent with the observed phase-locking of ENSO in the far eastern Pacific. It is shown that ENSO decadal or interdecadal variability may result from the nonlinear interactions between the annual and interannual cycles in the Tropics.