I.A. Sidorov1, E.P. Novichikhin2, S.V. Agasieva3, G.A. Gudkov4, S.V. Chizhikov5

1,4,5 Bauman Moscow State Technical University (Moscow, Russia)
2 Institute of Radioengineering and Electronics of Russian Academy of Sciences (Fryazino, Moscow Region, Russia)
3 Patrice Lumumba Peoples' Friendship University of Russia (Moscow, Russia)
1 igorasidorov@yandex.ru

The most common methods for determining the biophysical characteristics of soil and vegetation are based on the use of physical radiation models that establish a relationship between the measured radio brightness temperature and the parameters under study. However, the conversion task is a complex computational problem, which requires increasing the measurement error to simplify it. An alternative is neural network algorithms with high input data processing performance.

Objective – to model neural network algorithms for assessing the biophysical characteristics of the soil-vegetation system and to estimate the errors in the results of determining soil moisture and temperature and the specific density of vegetation phytomass.

The results of modeling neural network algorithms for assessing the biophysical characteristics of the soil-vegetation system are presented. The errors in the estimates of soil moisture and specific density of vegetation phytomass obtained using neural network algorithms in relation to the exact values in the field of operating parameters of physical radiation models are determined. The simulation was performed using single-channel and two-channel radiometric input data without noise and in the presence of additive Gaussian noise.

The results of the conducted research can be used to evaluate the possibility of using neural network algorithms to determine the biophysical characteristics of the soil-vegetation system.

1. Basharinov A.E., Shutko A.M. Opredelenie vlazhnosti zemnyh pokrovov metodami SVCh-radiometrii (obzor). Radiotekhnika i elektronika. 1978. T. 23. № 9. S. 1778–1791 (in Russian).
2. Chuhlancev A.A., Shutko A.M. Primenenie SVCh-radiometricheskogo metoda dlya opredeleniya biometricheskih harakteristik rastitel'nyh pokrovov. Issledovanie Zemli iz kosmosa. 1987. № 5. S. 42–47 (in Russian).
3. Chuhlancev A.A., Shutko A.M. Ob uchete vliyaniya rastitel'nosti pri distancionnom SVCh-radiometricheskom zondirovanii zemnyh pokrovov. Issledovanie Zemli iz kosmosa. 1988. № 2. S. 67–72 (in Russian).
4. Shou-Fang Liu, Yuei-An Liou, Wen-Jun Wang, Wigneron J.P. Retrieval of crop biomass and soil moisture from measured 1.4 and 10.65 GHz brightness temperatures. IEEE Transactions on Geosci. Remote Sens. 2002. V. GE-40. № 6. P. 1260–1268.
5. Owe M., Jeu R., Walker J. A methodology for surface soil moisture and vegetation depth retrieval using the microwave polarization difference index. IEEE Transactions on Geosci. Remote Sens. 2001. V. GE-39. № 8. P. 1643–1654.
6. Njoku F.G., Wilson W.J., Yueh S.H., Dinardo S.J.,Li F.L., Jackson T.J., Lakshmi V., Bolten J. Observations of soil moisture using a passive and active low-frequency microvave airborne sensor during SGP99. IEEE Transactions on Geosci. Remote Sens. 2002. V. GE-40. № 12. P. 2659–2673.
7. Njoku F.G., Jackson T.J., Lakshmi V., Chan T.K., Nghiem S.V. Soil moisture retrieval from AMSR-E. IEEE Transactions on Geosci. Remote Sens. 2003. V. GE-41. № 2. P. 215–2229.
8. Kirdyashev K.P., Chuhlancev A.A., Shutko A.M. SVCh-izluchenie zemnoj poverhnosti pri nalichii rastitel'nogo pokrova. Radiotekhnika i elektronika. 1979. T. 24. № 2. S. 256–264 (in Russian).
9. Wang J.R., Schmugge T.J. An empirical model for the complex dielectric permitivity of soils as function of water content. IEEE Transactions on Geosci. Remote Sens. 1980. V. GE-18. P. 288–295.
10. Dobson M.C., Ulaby F.T., Hallikainen M.T., El-Rayes M.A. Microwave dielectric behavior of wet soil – part II: dielectric mixing models. IEEE Transactions on Geosci. Remote Sens. 1985. V. GE-23. P. 35–46.
11. Njoku E.G., Kong J.F. Theory for passive microwave remote sensing of near-surface soil moisture. J. Geophys. Res. 1977. V. 82.
    P. 3208–3118.
12. Mo F.T., Schmugge T.J., Jackson T.J. Calculation of radar backscattering coefficient of vegetation-covered soil. Remote Sensing Environ. 1984. V. 15. P. 119–133.
13. Eom H.J. Regression models for vegetation radar-backscattering and radiometric emission. Remote Sensing Environ. 1986. V.19.
    P. 151–157.
14. Yuei-An Liou, Tzeng Y.C., Chen K.S. A neural-network approach to radiometric sensing of land-surface parameters. IEEE Transactions on Geosci. Remote Sens. 1999. V. GE-37. P. 2718–2724.
15. Yuei-An Liou, Shou-Fang Liu, Wen-June Wang. Retrieving soil moisture from simulated brightness temperatures by neural network. IEEE Transactions on Geosci. Remote Sens. 2001. V. GE-39. № 8. P. 1662–1672.
16. Nazarov L.E., Marechek S.V., Tishchenko Yu.G., Golovachev S.P., Chuhlancev A.A., Shutko A.M. Nejrosetevye algoritmy polucheniya biometricheskih harakteristik rastitel'nyh pokrovov na osnove analiza radiolokacionnyh izobrazhenij: Trudy nauchnoj sessii, posvyashchennoj Dnyu Radio. Tom 1. Moskva. 2003. 14–15 maya. S. 148–150 (in Russian).
17. Nazarov L.E., Chuhlancev A.A., Shutko A.M., Golovachev S.P. Nejrosetevye algoritmy ocenki vlazhnosti pochvy s ispol'zovaniem dannyh passivnoj SVCh-radiometrii. Nejrokomp'yutery: razrabotka, primenenie. 2003. № 12. S. 20–32 (in Russian).
18. Nazarov L.E., Chuhlancev A.A., Shutko A.M. Nejrosetevye algoritmy ocenki vlazhnosti pochvy po dannym SVCh-radiometricheskih izmerenij. Issledovaniya Zemli iz kosmosa. 2004. № 5. S. 1–9 (in Russian).
19. Choudhury B.J., Schmugge T.J., Newton R.W., Chang A.T.C. Effect of surface roughness on microwave emission of soils. J. Geophys. Res. 1979. № 84. P. 5699–5706.
20. Adab H., Morbidelli R., Saltalippi C., Moradian M., Ghalhari G.A.F. Machine Learning to Estimate Surface Soil Moisture from Remote Sensing Data. Water. 2020. V. 12. P. 3223.
21. Souissi R., Bitar A., Zribi M. Accuracy and Transferability of Artificial Neural Networks in Predicting in Situ Root-Zone Soil Moisture for Various Regions across the Globe. Water. 2020. V. 12. P. 3109.
22. Elshorbagy A., Parasuraman K. On the relevance of using artificial neural networks for estimating soil moisture content. Journal of Hydrology. 2008. V. 362. P. 1–18.
23. Moosavi V., Talebi A., Mokhtari M.H., Hadian M.R. Estimation of spatially enhanced soil moisture combining remote sensing and artificial intelligence approaches. International Journal of Remote Sensing. 2016. V. 37. № 23. P. 5605–5631.
24. Karandish F., Simunek J. A comparison of numerical and machine-learning modeling of soil water content with limited input data. Journal of Hydrology. 2016. V. 543. P. 892–909.
25. Bermeo C.L., Palacio M.G., Cano L.S., Ramírez R.M., Montoya C.H. Comparison of Machine Learning Parametric and Non-Parametric Techniques for Determining Soil Moisture: Case Study at Las Palmas Andean Basin. Advances in Science, Technology and Engineering Systems Journal. 2021. V. 6. № 1. P. 636–650.
26. Marini A., Termite L.E., Garinei A., Marconi M., Biondi L. Neural network models for soil moisture forecasting from remotely sensed measurements. ACTA IMEKO. June 2020. V. 9. № 2. P. 59–65.
27. Uthayakumar A., Mohan M.P., Khoo E.H., Jimeno J., Siyal M.Y., Karim M.F. Machine Learning Models for Enhanced Estimation of Soil Moisture Using Wideband Radar Sensor. Sensors. 2022. V. 22. P. 5810.
28. Haykin S. Neural networks. A comprehensive foundation. Second edition. Prentice Hall 07458. New Jersey. 1998.
29. Tihonov A.N., Arsenin V.O. Metody resheniya nekorrektnyh zadach. Izd. 2. M.: Nauka.1979 (in Russian).
30. Gudkov A.G., Sidorov I.A., Novichihin E.P. i dr. Radiometriya. M.: Izdatel'skij Dom «Nauchnaya biblioteka». 2024. 336 s. (in Russian).