Classification of Soil Groups Using Weights-of-Evidence-Method and RBFLN-Neural Nets
Tóm tắt
Weights-of-Evidence (WofE) and Radial Basis Function Link Net (RBFLN) were applied to soil group mapping in eastern Finland. The data consisted of low altitude airborne geophysical measurements, Landsat 5 TM-satellite image, and digital elevation model (DEM) and slope information derived from it. Probability maps were constructed for each soil group one by one and combined into a prediction map of soil groups using maximum posterior probability (WofE) or pattern membership (RBFLN). Self-Organizing Map (SOM) and Sammon’s Mapping were applied for selecting the data sets for modeling and visualizing the data. The soil types belonging to each soil group used in the Arc-SDM modeling were defined by clusters revealed by the SOM and Sammon’s Mapping algorithms. The soil types with similar characters were collected in the same cluster. Numerical evaluation of the models’ performance was performed using the confusion matrix. The Ratio of Correct Classifications (RCC) for the best WofE model was 0.64 in the training area and 0.61 in the testing area. The RCC for the best RBFLN model was 0.62. Modeling of soil groups using Arc-SDM is time consuming because models need to be constructed for each soil group before combining them into a final prediction map. In this study a simple method was tested for combining the maps. In the future, more attention should be paid to combining the posterior probability models and also to selecting data sets used for modeling.
Tài liệu tham khảo
Airo, M.-L., ed., 2005, Aerogeophysics in Finland 1972–2004: methods, system characteristics and applications: Geol. Survey Finland, Spec. Paper 39, 197 p
Haavisto, M., ed., 1983, Maaperäkartan käyttöopas 1:20,000, 1:50,000: Geologinen tutkimuslaitos. Opas 10. Espoo, 80 p
Harris J. R., Wilkinson L., Heather K., Fumerton S., Bernier M. A., Ayer J., Dahn R., 2001, Application of GIS processing techniques for producing mineral prospectivity maps – A case study: Mesothermal Au in the Swayze Greenstone Belt, Ontario, Canada. Natural Resources Research, 10(2), 91–124
Itkonen, A., 1991, Aerogammamittausten käyttömahdollisuuksista maaperäkartoituksen apuna. Syventävien opintojen tutkielma. Turun yliopisto: Maaperägeologian osasto, 94 p
Kejonen, A., and Saarelainen, J., 1992–2006, Maaperäkartat 1:20,000. Karttalehdet 3332 01–12 sekä niiden selostukset: Geologian tutkimuskeskus ja Maanmittauslaitos
Kemp, L. D., Bonham-Carter, G. F., and Raines, G. L., 1999, Arc-WofE: Arcview extension for weights of evidence mapping. http://www.ige.unicamp.br/wofe
Kemp, L. D., Bonham-Carter, G. F., Raines, G. L., and Looney, C. G., 2001, Arc-SDM: Arcview extension for spatial data modelling using weights of evidence, logistic regression, fuzzy logic and neural network analysis. http://www.ige.unicamp.br/sdm/
Kohonen T., 1997, Self-oganizing maps, (2nd edn). Springer-Verlag, Berlin, Heidelberg, Germany, 426 p
Kolehmainen M., Rönkkö P., Raatikainen O., 2003, Monitoring of yeast fermentation by ion mobility distribution measurement and data visualisation with self-organizing maps. Analytica Chemica Acta, 484, 93–100
Koljonen T., Tanskanen H., 1992, Quaternary sediments (p. 40–49), in Koljonen T eds., The Geochemical Atlas of Finland, P 2: Till. Geol. Survey Finland, Espoo, 218 p
Kujansuu, R., and Niemelä, J., 1984, Suomen maaperä 1:1000000. Finlands kvartära avlagningar. Quaternary deposits of Finland: Geol. Survey Finland, Spec. Maps, No. 13
Looney, C. G., 1999, Lecture notes: Training workshop on Arc-SDM and DataXplore: Geol. Survey Canada. http://www.ige.unicamp.br/sdm/doc/documentation/neuralnet.htm
Nevalainen, R., 2002, Maaperän yleiskartoitus paikkatietoaineistojen ja GIS-analyysien avulla. Julkaisussa Putkinen, N. & Lunkka, J.P. (toim.): Uudet kartoitustekniikat ja niiden hyödyntäminen kvartääritutkimuksessa. Seminaari, Tvärminne 7. - 8.11.2002. 11 p.
Nevalainen, R., Hyvönen, E., Lerssi, J., Liwata, P., Middleton, M., Palmu, J. P., Virkki, H., and Väänänen, T., 2002, Maaperän yleiskartoitus paikkatietoaineistojen ja -analyysien avullauuden alueellisesti kattavan tietovaraston kerääminen, in Pietola, L., and Esala, M. (toim.): Maa, josta elämme. II Maaperätieteiden päivien laajennetut abstraktit: Pro Terra No. 15. Helsinki 2002. ISBN 952100780X, 148 p
Nykänen, V., and Salmirinne, H., 2007, Prospectivity analysis of gold using regional geophysical and geochemical data from the Central Lapland Greenstone Belt, Finland, in Nurmi P., and Ojala J., eds., Gold in the Central Lapland Greenstone Belt: Geol. Survey Finland, Spec. Paper 44, in press
Peltoniemi, M., 1998, Maa- ja kallioperän geofysikaaliset tutkimusmenetelmät: Otakustantamo No 515, Espoo. ISBN 951-672-050-0, 411 p
Raines G. L., 1999, Evaluation of weights of evidence to predict epithermal-gold deposits in the great basin of the western United States. Natural Resources Research, 8(4), 257–276
Sammon Jr. J. W., 1969, A nonlinear mapping for data structure analysis. IEEE Trans. Computers, C-18, 401–409
Tissari, S., 2003, Classification of surficial soil deposits using weights-of-evidence and RBFLN-neural nets: published in Finnish masters thesis, Univ. Kuopio, 112 p
Yli-Halla M., Talkkari, A., Nyholm, R., Nevalainen, R., Lerssi, J., Väänänen, T., Tamminen, P., and Starr, M., 2003, Numeerinen Suomen maannostietokanta mittakaavassa 1:250,000 – pilottihanke. MTT:n selvityksiä 44. 54 s. http://www.mtt.fi/mtts/pdf/mtts44.pdf