It is critically meaningful to accurately predict the ionospheric F2 layer critical frequency (foF2), which greatly limits the efficiency of communications, radar, and navigation systems. This paper introduced the entropy weight method to develop the combination prediction model (CPM) for long-term foF2 at Darwin (12.4° S, 131.5° E) in Australia. The weight coefficient of each individual model in the CPM is determined by using the entropy weight method after completing the simulation of the individual model in the calibration period. We analyzed two sets of data to validate the method used in this study: One set is from 2000 and 2009, which are included in the calibration period (1998–2016), and the other set is outside the calibration cycle (from 1997 and 2017). To examine the performance, the root mean square error (RMSE) of the observed monthly median foF2 value, the proposed CPM, the Union Radio Scientifique Internationale (URSI), and the International Radio Consultative Committee (CCIR) are compared. The yearly RMSE average values calculated from CPM were less than those calculated from URSI and CCIR in 1997, 2000, 2009, and 2017. In 2000 and 2009, the average percentage improvement between CPM and URSI is 9.01%, and the average percentage improvement between CPM and CCIR is 13.04%. Beyond the calibration period, the average percentage improvement between CPM and URSI is 13.2%, and the average percentage improvement between CPM and CCIR is 12.6%. The prediction results demonstrated that the proposed CPM has higher precision of prediction and stability than that of the URSI and CCIR, both within the calibration period and outside the calibration period.

A model based on modified temporal‐spatial reconstruction is proposed to improve the accuracy of predicting the monthly median ionospheric critical frequency of the F2 layer. This model has three new characteristics. (1) The solar activity parameters of the 10.7‐cm solar radio flux and sunspot number are together introduced into temporal reconstruction. (2) Both the geomagnetic dip and its modified value are chosen as features of the geographical spatial variation for spatial reconstruction. (3) Harmonic functions are used to represent the ionospheric critical frequency of the F2 layer, which reflects seasonal and solar cycle variations. Furthermore, combining the least squares fitting regression for these characteristics with harmonic analysis, a valid model can be established from vertical sounding data spread across three ionospheric regions (high, middle, and low latitudes in Asia). Statistical results reveal that the ionospheric critical frequency of the F2 layer calculated by the proposed model is consistent with the trend of the monthly median observations. The average root‐mean‐square error is only 0.70 MHz (corresponding to relative error 11.30%), reflecting that our model outperforms the International Reference Ionosphere model with International Union of Radio Science and Consultative Committee on International Radio (CCIR) coefficients. Moreover, the proposed method has great potential in terms of providing higher prediction accuracy for ionospheric parameters on the global scale.

In order to predict the livestock carrying capacity in meadow steppe, a method using back propagation neural network is proposed based on the meteorological data and the remote-sensing data of Normalised Difference Vegetation Index. In the proposed method, back propagation neural network was first utilised to build a behavioural model to forecast precipitation during the grass-growing season (June–July–August) from 1961 to 2015. Second, the relationship between precipitation and Normalised Difference Vegetation Index during the grass-growing season from 2000 to 2015 was modelled with the help of back propagation neural network. The prediction results demonstrate that the proposed back propagation neural network-based model is effective in the forecast of precipitation and Normalised Difference Vegetation Index. Thus, an accurate prediction of livestock carrying capacity is achieved based on the proposed back propagation neural network-based model. In short, this work can be used to improve the utilisation of grassland and prevent the occurrence of vegetation degradation by overgrazing in drought years for arid and semiarid grasslands.