Sciences in Cold and Arid Regions ›› 2018, Vol. 10 ›› Issue (6): 468-481.doi: 10.3724/SP.J.1226.2018.00468

Previous Articles     Next Articles

Simulation and prediction of monthly accumulated runoff, based on several neural network models under poor data availability

JianPing Qian1,JianPing Zhao1,Yi Liu2,3,XinLong Feng1,DongWei Gui2,3,*()   

  1. 1 College of Mathematics and System Sciences, Xinjiang University, Urumqi, Xinjiang 830046, China
    2 State Key Laboratory of Desert and Oasis Ecology, Xinjiang Institute of Ecology and Geography, Chinese Academy of Sciences, Xinjiang 830011, China
    3 Cele National Station of Observation and Research for Desert–Grassland Ecosystem, Xinjiang Institute of Ecology and Geography, Chinese Academy of Sciences, Urumqi, Xinjiang 830011, China
  • Received:2018-03-09 Accepted:2018-09-05 Online:2018-12-01 Published:2018-12-29
  • Contact: DongWei Gui E-mail:guidwei@ms.xjb.ac.cn
  • Supported by:
    This work was financially supported by the regional collaborative innovation project for Xinjiang Uygur Autonomous Region (Shanghai cooperation organization science and technology partnership project) (2017E01029), the "Western Light" program of the Chinese Academy of Sciences (2017-XBQNXZ-B-016), the National Natural Science Foundation of China (41601595, U1603343, 41471031), and the State Key Laboratory of Desert and Oasis Ecology, Xinjiang Institute of Ecology and Geography, Chinese Academy of Sciences (G2018-02-08).

Abstract:

Most previous research on areas with abundant rainfall shows that simulations using rainfall-runoff modes have a very high prediction accuracy and applicability when using a back-propagation (BP), feed-forward, multilayer perceptron artificial neural network (ANN). However, in runoff areas with relatively low rainfall or a dry climate, more studies are needed. In these areas—of which oasis-plain areas are a particularly good example—the existence and development of runoff depends largely on that which is generated from alpine regions. Quantitative analysis of the uncertainty of runoff simulation under climate change is the key to improving the utilization and management of water resources in arid areas. Therefore, in this context, three kinds of BP feed-forward, three-layer ANNs with similar structure were chosen as models in this paper. Taking the oasis–plain region traverse by the Qira River Basin in Xinjiang, China, as the research area, the monthly accumulated runoff of the Qira River in the next month was simulated and predicted. The results showed that the training precision of a compact wavelet neural network is low; but from the forecasting results, it could be concluded that the training algorithm can better reflect the whole law of samples. The traditional artificial neural network (TANN) model and radial basis-function neural network (RBFNN) model showed higher accuracy in the training and prediction stage. However, the TANN model, more sensitive to the selection of input variables, requires a large number of numerical simulations to determine the appropriate input variables and the number of hidden-layer neurons. Hence, The RBFNN model is more suitable for the study of such problems. And it can be extended to other similar research arid-oasis areas on the southern edge of the Kunlun Mountains and provides a reference for sustainable water-resource management of arid-oasis areas.

Key words: oasis, artificial neural network, radial basis function, wavelet function, runoff simulation

Figure 1

Location and topography of the study area"

Figure 2

Schematic diagram of a three-layered ANN"

Table 1

Statistical analysis of MAR, MAP, MMT, and MAE time-series data"

Variable Training Testing
min max mean Sd CSX min max mean Sd CSX
Runoff 53.6 6,797.8 1,086.2 1,446.7 1.73 46.3 5,080.9 958.5 1,245.9 1.47
Precipitation 0.0 34.0 3.1 5.8 2.73 0.0 15.3 2.1 3.2 2.10
Temperature ?8.5 27.1 12.3 10.6 ?0.30 ?8.9 27.5 13.4 10.9 ?0.40
Evaporation 3.7 503.1 233.8 137.3 ?0.02 20.2 464.9 240.8 141.2 ?0.08

Figure 3

Time-series of (a) monthly average temperature and monthly accumulated evaporation and (b) monthly accumulated precipitation and monthly accumulated runoff"

Table 2

Evaluation results regarding the model performance of TANN, CWNN, and RBFNN"

Model type Model No. Input variables Number of
hidden neurons
Training Testing
R2 NSE PBLAS R2 NSE PBLAS
TANN A1 1p1e1r1c1t 7 0.955 0.971 0.29 0.009 ?0.016 16.60
TANN A2 2p1e1r1c1t 7 0.967 0.979 1.01 0.580 0.592 ?27.86
TANN A3 3p1e1r1c1t 7 0.976 0.985 1.53 0.664 0.663 ?16.11
TANN A4 4p1e1r1c1t 7 0.979 0.986 1.61 0.724 0.696 ?13.41
CWNN A5 1p1e1r1c1t 7 0.852 0.906 0.77 0.417 0.252 ?7.82
CWNN A6 2p1e1r1c1t 7 0.876 0.920 2.27 0.676 0.665 ?0.10
CWNN A7 3p1e1r1c1t 7 0.906 0.940 ?1.34 0.770 0.764 ?6.21
CWNN A8 4p1e1r1c1t 7 0.890 0.930 1.32 0.788 0.839 ?6.21
RBFNN A9 1p1e1r1c1t 0.947 0.966 ?0.71 0.031 ?0.290 18.26
RBFNN A10 2p1e1r1c1t 0.946 0.965 0.24 0.627 0.654 ?9.41
RBFNN A11 3p1e1r1c1t 0.946 0.965 0.00 0.705 0.756 ?2.71
RBFNN A12 4p1e1r1c1t 0.946 0.966 ?0.01 0.847 0.880 ?6.72

Table 3

Input structure of the ANN, WNN and RBFNN models for runoff modelling"

Model No. Input variables Explaining variable
1 1p1t1r P(t-1), t, R(t-1)
2 2p1t P(t-1), P(t-2), t
3 2p1t1c P(t-1), P(t-2), t, T(t-1)
4 3p1t P(t-1), P(t-2), P(t-3), t
5 3p1t1r P(t-1), P(t-2), P(t-3), t, R(t-1)
6 3p1t1c P(t-1), P(t-2), P(t-3), t, T(t-1)
7 4p1t P(t-1), P(t-2), P(t-3), P(t-4), t
8 4p1t1r P(t-1), P(t-2), P(t-3), P(t-4), t, R(t-1)

Table 4

Evaluation results of the TANN model's performances"

Model No. Input variables Number of
hidden neurons
Training Testing
R2 NSE PBLAS R2 NSE PBLAS
B1 1p1t1r 6 0.895 0.933 0.08 0.860 0.870 ?17.27
B2 2p1t 7 0.891 0.931 0.29 0.897 0.924 ?12.05
B3 2p1t1c 6 0.940 0.962 1.43 0.886 0.920 ?6.41
B4 3p1t 4 0.903 0.938 ?0.09 0.901 0.933 ?9.71
B5 3p1t1r 6 0.955 0.971 0.41 0.839 0.894 ?3.56
B6 3p1t1c 5 0.935 0.958 0.70 0.872 0.880 ?16.26
B7 4p1t 5 0.923 0.951 2.79 0.835 0.853 ?17.70
B8 4p1t1r 3 0.903 0.938 ?0.26 0.883 0.922 ?7.98

Table 5

Evaluation results of the CWNN model's performances"

Model No. Input variables Number of
hidden neurons
Training Testing
R2 NSE PBLAS R2 NSE PBLAS
C1 1p1t1r 5 0.776 0.857 1.49 0.440 0.297 ?13.40
C2 2p1t 9 0.884 0.926 0.15 0.898 0.883 ?10.49
C3 2p1t1c 6 0.880 0.923 ?0.09 0.896 0.890 ?8.72
C4 3p1t 6 0.882 0.925 0.37 0.889 0.860 ?12.29
C5 3p1t1r 7 0.887 0.928 0.35 0.877 0.868 ?6.53
C6 3p1t1c 5 0.869 0.916 0.39 0.890 0.883 ?8.16
C7 4p1t 7 0.871 0.918 0.23 0.901 0.886 ?8.89
C8 4p1t1r 8 0.901 0.937 1.21 0.874 0.853 7.19

Table 6

Evaluation results of the RBFNN model's performances"

Model No. Input variables Training Testing
R2 NSE PBLAS R2 NSE PBLAS
D1 1p1t1r 0.891 0.930 0.14 0.432 0.557 ?3.52
D2 2p1t 0.894 0.933 ?0.21 0.892 0.916 ?14.83
D3 2p1t1c 0.910 0.942 ?0.12 0.870 0.889 ?13.20
D4 3p1t 0.924 0.952 ?0.87 0.870 0.909 ?12.19
D5 3p1t1r 0.963 0.976 ?1.50 0.813 0.872 ?3.76
D6 3p1t1c 0.935 0.959 0.26 0.811 0.828 ?21.30
D7 4p1t 0.919 0.948 ?0.01 0.887 0.877 ?19.87
D8 4p1t1r 0.918 0.948 ?0.02 0.906 0.916 ?15.52

Figure 4

Regression plots displaying the training and testing results of the TANN model B4, CWNN model C3, and RBFNN model D8"

Figure 5

Comparison of observed data and predictions for the (a) TANN model B4, (b) CWNN model C3, and (c) RBFNN model D8"

1 Adamowski J, Chan HF A wavelet neural network conjunction model for groundwater level forecasting. Journal of Hydrology 2011; 407: 1–4 28- 40.
doi: 10.1016/j.jhydrol.2011.06.013
2 Beale M, Demuth H, 1998. Neural Network Toolbox for Use with MATLAB, User's guide. Works, Natick: The Math, pp. 1–6.
3 Boehmer K, Memon A, Mitchell B Towards sustainable water management in Southeast Asia—experiences from Indonesia and Malaysia. Water International 2000; 25: 3 356- 377.
doi: 10.1080/02508060008686843
4 Bowden GJ, Dandy GC, Maierb HR Input determination for neural network models in water resources applications. Part 1- Background and methodology. Journal of Hydrology 2005a; 301: 1–4 75- 92.
doi: 10.1016/j.jhydrol.2004.06.021
5 Bowden GJ, Maierb HR, Dandy GC Input determination for neural network models in water resources applications. Part 2. Case study: Forecasting salinity in a river. Journal of Hydrology 2005b; 301: 1–4 93- 107.
doi: 10.1016/j.jhydrol.2004.06.020
6 Campolo M, Soldati A, Andreussi P Artificial neural network approach to flood forecasting in the River Arno. Hydrological Sciences Journal 2003; 48: 3 381- 398.
doi: 10.1623/hysj.48.3.381.45286
7 Cannas B, Fanni A, See L, et al. Data preprocessing for river flow forecasting using neural networks: wavelet transforms and data partitioning. Physics and Chemistry of the Earth, Parts A/B/C 2006; 31: 18 1164- 1171.
doi: 10.1016/j.pce.2006.03.020
8 Chapman L, Thornes JE The use of geographical information systems in climatology and meteorology. Progress in Physical Geography 2003; 27: 3 313- 330.
doi: 10.1191/030913303767888464
9 Chen XY, Chau KW, Busari AO A comparative study of population-based optimization algorithms for downstream river flow forecasting by a hybrid neural network model. Engineering Applications of Artificial Intelligence 2015; 46: 258- 268.
doi: 10.1016/j.engappai.2015.09.010
10 Chen YN, Xu CC, Hao XM, et al. Fifty-year climate change and its effect on annual runoff in the Tarim River Basin, China. Quaternary International 2009; 208: 1–2 53- 61.
doi: 10.1016/j.quaint.2008.11.011
11 Chen YN, 2014. Water Resources Research in Northwest China. Dordrecht: Springer, pp. 1–20. DOI: 10.1007/978-94-017-8017-9.
12 Dai SY, Lei JQ, Zhao JF, et al. Groundwater characteristics and their effects to eco-environmental of desert-oasis transitional zone in western Qira. Journal of Arid Land Resources and Environment 2009a; 23: 8 99- 103.
13 Dai SY, Lei JQ, Zhou JF, et al. Changing trend and features of the runoff from mountain areas of the Qira River. Arid Land Geography 2009b; 32: 2 204- 210.
14 Dawson CW, Wilby RL Hydrological modelling using artificial neural networks. Progress in Physical Geography 2001; 25: 1 80- 108.
doi: 10.1177/030913330102500104
15 Fang KY, Gou XH, Chen FH, et al. Large-scale precipitation variability over Northwest China inferred from tree rings. Journal of Climate 2011; 24: 13 3457- 3468.
doi: 10.1175/2011JCLI3911.1
16 Grossmann A, Morlet J Decomposition of hardy functions into square integrable wavelets of constant shape. SIAM Journal on Mathematical Analysis 1984; 15: 4 723- 736.
doi: 10.1137/0515056
17 Gupta HV, Sorooshian S, Yapo PO Status of automatic calibration for hydrologic models: comparison with multilevel expert calibration. Journal of Hydrologic Engineering 1999; 4: 2 135- 143.
doi: 10.1061/(ASCE)1084-0699(1999)4:2(135)
18 Hagan MT, Menhaj MB Training feedforward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks 1994; 5: 6 989- 993.
doi: 10.1109/72.329697
19 Ham FM, Kostanic I, 2000. Principles of Neurocomputing for Science and Engineering. New York: McGraw-Hill Higher Education.
20 Hu TS, Lam KC, Ng ST A modified neural network for improving river flow prediction. Hydrological Sciences Journal 2005; 50: 2 318.
doi: 10.1623/hysj.50.2.299.61794
21 Jain SK, Das A, Srivastava DK Application of ANN for reservoir inflow prediction and operation. Journal of Water Resources Planning and Management 1999; 125: 5 263- 271.
doi: 10.1061/(ASCE)0733-9496(1999)125:5(263)
22 Jeffrey SJ, Carter JO, Moodie KB, et al. Using spatial interpolation to construct a comprehensive archive of Australian climate data. Environmental Modelling & Software 2001; 16: 4 309- 330.
doi: 10.1016/S1364-8152(01)00008-1
23 Kim CK, Kwak IS, Cha EY et al. Implementation of wavelets and artificial neural networks to detection of toxic response behavior of chironomids (Chironomidae: Diptera) for water quality monitoring. Ecological Modelling 2006; 195: 1–2 61- 71.
doi: 10.1016/j.ecolmodel.2005.11.010
24 Kisi O, Cigizoglu HK Comparison of different ANN techniques in river flow prediction. Civil Engineering and Environmental Systems 2007; 24: 3 211- 231.
doi: 10.1080/10286600600888565
25 Labat D, Ababou R, Mangin A Rainfall-runoff relations for Karstic springs. Part II: continuous wavelet and discrete orthogonal multiresolution analyses. Journal of Hydrology 2000; 238: 3–4 149- 178.
doi: 10.1016/S0022-1694(00)00322-X
26 Li XM, Jiang FQ, Li LH, et al. Spatial and temporal variability of precipitation concentration index, concentration degree and concentration period in Xinjiang, China. International Journal of Climatology 2011a; 31: 11 1679- 1693.
doi: 10.1002/joc.2181
27 Li XM, Li LH, Guo LP, et al. Impact of climate factors on runoff in the Kaidu River watershed: path analysis of 50-year data. Journal of Arid Land 2011b; 3: 2 132- 140.
doi: 10.3724/SP.J.1227.2011.00132
28 Li XM, Li LH, Wang XX, et al. Reconstruction of hydrometeorological time series and its uncertainties for the Kaidu River Basin using multiple data sources. Theoretical and Applied Climatology 2013; 113: 1–2 45- 62.
doi: 10.1007/s00704-012-0771-2
29 Licznar P, Nearing MA Artificial neural networks of soil erosion and runoff prediction at the plot scale. CATENA 2003; 51: 2 89- 114.
doi: 10.1016/S0341-8162(02)00147-9
30 Ling HB, Xu HL, Shi W, et al. Regional climate change and its effects on the runoff of Manas River, Xinjiang, China. Environmental Earth Sciences 2011; 64: 8 2203- 2213.
doi: 10.1007/s12665-011-1048-2
31 Mallat S, 1998. A wavelet tour of signal processing. New York: Academic.
32 Meng LH, Chen YN, Li WH, et al. Fuzzy comprehensive evaluation model for water resources carrying capacity in Tarim River Basin, Xinjiang, China. Chinese Geographical Science 2009; 19: 1 89- 95.
doi: 10.1007/s11769-009-0089-x
33 Moody J, Darken C Speedy alternatives to back propagation. Neural Networks 1988; 1: 202- 202.
doi: 10.1016/0893-6080(88)90239-0
34 Moriasi DN, Arnold JG, Van Liew MW, et al. Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Transactions of the ASABE 2007; 50: 3 885- 900.
doi: 10.13031/2013.23153
35 Nilsson P, Uvo CB, Berndtsson R Monthly runoff simulation: comparing and combining conceptual and neural network models. Journal of Hydrology 2006; 321: 1–4 344- 363.
doi: 10.1016/j.jhydrol.2005.08.007
36 Ninyerola M, Pons X, Roure MJ A methodological approach of climatologically modelling of air temperature and precipitation through GIS techniques. International Journal of Climatology 2000; 20: 14 1823- 1841.
doi: 10.1002/1097-0088(20001130)20:14<1823::AID-JOC566>3.0.CO;2-B
37 Nourani V, Alami MT, Aminfar MH A combined neural-wavelet model for prediction of Ligvanchai watershed precipitation. Engineering Applications of Artificial Intelligence 2009a; 22: 3 466- 472.
doi: 10.1016/j.engappai.2008.09.003
38 Nourani V, Komasi M, Mano A A multivariate ANN-wavelet approach for rainfall-runoff modeling. Water Resources Management 2009b; 23: 14 2877- 2894.
doi: 10.1007/s11269-009-9414-5
39 Partal T, Kişi O Wavelet and neuro-fuzzy conjunction model for precipitation forecasting. Journal of Hydrology 2007; 342: 1–2 199- 212.
doi: 10.1016/j.jhydrol.2007.05.026
40 Pramanik N, Panda RK, Singh A Daily river flow forecasting using wavelet ANN hybrid models. Journal of Hydroinformatics 2011; 13: 1 49- 63.
doi: 10.2166/hydro.2010.040
41 Salas JD, Markus M, Tokar AS, 2000. Streamflow forecasting based on artificial neural networks. In: Govindaraju RS, Ramachandra Rao A (eds.). Artificial Neural Networks in Hydrology. Dordrecht: Kluwer Academic, 23–51.
42 Skirvin SM, Marsh SE, McClaranw MP, et al. Climate spatial variability and data resolution in a semi-arid watershed, south-eastern Arizona. Journal of Arid Environments 2003; 54: 4 667- 686.
doi: 10.1006/jare.2002.1086
43 Srinivasulu S, Jain A A comparative analysis of training methods for artificial neural network rainfall-runoff models. Applied Soft Computing 2006; 6: 3 295- 306.
doi: 10.1016/j.asoc.2005.02.002
44 Sun HW, Gui DW, Yan BW, et al. Assessing the potential of random forest method for estimating solar radiation using air pollution index. Energy Conversion and Management 2016; 119: 121- 129.
doi: 10.1016/j.enconman.2016.04.051
45 Wang W, van Gelder PHAJM, Vrijling JK, et al. Forecasting daily streamflow using hybrid ANN models. Journal of Hydrology 2006; 324: 1–4 383- 399.
doi: 10.1016/j.jhydrol.2005.09.032
46 Wu CL, Chau KW, Li YS Methods to improve neural network performance in daily flows prediction. Journal of Hydrology 2009; 372: 1–4 80- 93.
doi: 10.1016/j.jhydrol.2009.03.038
47 Wu JL, Yang FX, Zhou J, et al. Desert types and characteristics in the Qira River Basin. Arid Land Geography 2013; 36: 5 803- 811.
doi: 10.13826/j.cnki.cn65-1103/x.2013.05.007
48 Wu YW, Yang FX, Hua T Landforms and their effects on ecological pattern in the Qira River Basin. Arid Zone Research 2011; 28: 2 355- 362.
doi: 10.13866/j.azr.2011.02.019
49 Wu ZT, Zhang HJ, Krause CM, et al. Climate change and human activities: a case study in Xinjiang, China. Climate Chang 2010; 99: 3–4 457- 472.
doi: 10.1007/s10584-009-9760-6
50 Xue J, Gui DW, Zhao Y, et al. Quantification of environmental flow requirements to support ecosystem services of Oasis Areas: a case study in Tarim Basin, Northwest China. Water 2015; 7: 10 5657- 5675.
doi: 10.3390/w7105657
51 Xue J, Gui DW, Lei JQ, et al. Reconstructing meteorological time series to quantify the uncertainties of runoff simulation in the Ungauged Qira River basin using data from multiple stations. Theoretical and Applied Climatology 2016; 126: 1–2 61- 76.
doi: 10.1007/s00704-015-1548-1
52 Xue J, Gui DW, Lei JQ, et al. Model development of a participatory Bayesian network for coupling ecosystem services into integrated water resources management. Journal of Hydrology 2017a; 554: 50- 65.
doi: 10.1016/j.jhydrol.2017.08.045
53 Xue J, Gui DW, Lei JQ, et al. A hybrid Bayesian network approach for trade-offs between environmental flows and agricultural water using dynamic discretization. Advances in Water Resources 2017b; 110: 445- 458.
doi: 10.1016/j.advwatres.2016.10.022
54 Zhang B, Govindaraju RS Prediction of watershed runoff using bayesian concepts and modular neural networks. Water Resources Research 2000; 36: 3 753- 762.
doi: 10.1029/1999WR900264
[1] YuXin Zhang,Yu Li,XinZhong Zhang,ChengQi Zhang,WangTing Ye,Yuan Liu. A paleo-hydrological simulation experiment and its verification in an inland basin [J]. Sciences in Cold and Arid Regions, 2019, 11(4): 267-282.
[2] YongZhong Su,TingNa Liu,JunQia Kong. The establishment and development of Haloxylon ammodendron promotes salt accumulation in surface soil of arid sandy land [J]. Sciences in Cold and Arid Regions, 2019, 11(2): 116-125.
[3] CuiHua Huang,Fei Peng,Itaru Shibata,Jun Luo,Xian Xue,Kinya Akashi,Atsushi Tsunekawa,Tao Wang. Increase in medium-size rainfall events will enhance the C-sequestration capacity of biological soil crusts [J]. Sciences in Cold and Arid Regions, 2019, 11(1): 81-92.
[4] HaiYang Xi,JingTian Zhang,Qi Feng,Lu Zhang,JianHua Si,TengFei Yu. How changes of groundwater level affect the desert riparian forest ecosystem in the Ejina Oasis, Northwest China [J]. Sciences in Cold and Arid Regions, 2019, 11(1): 62-80.
[5] JianPing Yang, Man Li, ChunPing Tan, HongJu Chen, Qin Ji. Vulnerability and adaptation of an oasis social–ecological system affected by glacier change in an arid region of northwestern China [J]. Sciences in Cold and Arid Regions, 2019, 11(1): 29-40.
[6] HanChen Duan, Tao Wang, Xian Xue, CuiHua Huang, ChangZhen Yan. Quantitative retrieval of soil salt content based on measured spectral data [J]. Sciences in Cold and Arid Regions, 2016, 8(6): 507-515.
[7] JunJun Yang, ZhiBin He, WeiJun Zhao, Jun Du, LongFei Chen, Xi Zhu. Assessing artificial neural networks coupled with wavelet analysis for multi-layer soil moisture dynamics prediction [J]. Sciences in Cold and Arid Regions, 2016, 8(2): 116-124.
[8] HuaLi Tong, PeiJi Shi, GuoFeng Zhu, April Pearson, QianGuo Li, YuanFeng Liu, HaiLong Liu. The characteristics of oasis urban expansion and drive mechanism analysis: a case study on Ganzhou District in Hexi Corridor, China [J]. Sciences in Cold and Arid Regions, 2015, 7(3): 282-292.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] Mohan Bahadur Chand,Rijan Bhakta Kayastha. Study of thermal properties of supraglacial debris and degree-day factors on Lirung Glacier, Nepal[J]. Sciences in Cold and Arid Regions, 2018, 10(5): 357 -368 .
[2] AiHong Xie, ShiMeng Wang, YiCheng Wang, ChuanJin Li. Comparison of temperature extremes between Zhongshan Station and Great Wall Station in Antarctica[J]. Sciences in Cold and Arid Regions, 2018, 10(5): 369 -378 .
[3] YanZai Wang, YongQiu Wu, MeiHui Pan, RuiJie Lu. Comparison of two classification methods to identify grain size fractions of aeolian sediment[J]. Sciences in Cold and Arid Regions, 2018, 10(5): 413 -420 .
[4] YinHuan Ao, ShiHua Lyu, ZhaoGuo Li, LiJuan Wen, Lin Zhao. Numerical simulation of the climate effect of high-altitude lakes on the Tibetan Plateau[J]. Sciences in Cold and Arid Regions, 2018, 10(5): 379 -391 .
[5] Zhuo Ga, Za Dui, Duodian Luozhu, Jun Du. Comparison of precipitation products to observations in Tibet during the rainy season[J]. Sciences in Cold and Arid Regions, 2018, 10(5): 392 -403 .
[6] Rong Yang, JunQia Kong, ZeYu Du, YongZhong Su. Altitude pattern of carbon stocks in desert grasslands of an arid land region[J]. Sciences in Cold and Arid Regions, 2018, 10(5): 404 -412 .
[7] Yang Qiu, ZhongKui Xie, XinPing Wang, YaJun Wang, YuBao Zhang, YuHui He, WenMei Li, WenCong Lv. Effect of slow-release iron fertilizer on iron-deficiency chlorosis, yield and quality of Lilium davidii var. unicolor in a two-year field experiment[J]. Sciences in Cold and Arid Regions, 2018, 10(5): 421 -427 .
[8] Ololade A. Oyedapo,Joseph M. Agbedahunsi,H. C Illoh,Akinwumi J. Akinloye. Comparative foliar anatomy of three Khaya species (Meliaceae) used in Nigeria as antisickling agent[J]. Sciences in Cold and Arid Regions, 2018, 10(4): 279 -285 .
[9] YuMing Wei, XiaoFei Ma, PengShan Zhao. Transcriptomic comparison to identify rapidly evolving genes in Braya humilis[J]. Sciences in Cold and Arid Regions, 2018, 10(5): 428 -435 .
[10] FangLei Zhong, AiJun Guo, XiaoJuan Yin, JinFeng Cui, Xiao Yang, YanQiong Zhang. Sociodemographic characteristics, cultural biases, and environmental attitudes: An empirical application of grid-group cultural theory in Northwestern China[J]. Sciences in Cold and Arid Regions, 2018, 10(5): 436 -446 .