Automated high resolution mapping of coffee in Rwanda using an expert Bayesian network

International Journal of Applied Earth Observation and Geoinformation

Volumn 33, Issue 1, 2014, Pages 331-340

  Mukashema, A ^a,b   Veldkamp, A ^b   Vrieling, A ^b  

^a Rwanda Natural Resources Authority (RNRA)   (Rwanda)

^b UNIVERSITY OF TWENTE   (Netherlands)

Author keywords

Bayesian network; Coffee; Expert knowledge; Remote sensing; Rwanda; Very high resolution imagery

Indexed keywords

AERIAL PHOTOGRAPHY; AGRICULTURAL ECOSYSTEM; BAYESIAN ANALYSIS; COFFEE; EXPERT SYSTEM; MAPPING; REMOTE SENSING; SATELLITE IMAGERY; SPATIAL RESOLUTION;

RWANDA;

EID: 84904811239     PISSN: 15698432     EISSN: 1872826X     Source Type: Journal    
DOI: 10.1016/j.jag.2014.05.005     Document Type: Article

References (41)

1. Aguilera, P.A., Fernández, A., Reche, F., Rumí, R., 2010. Hybrid Bayesian networkclassifiers: application to species distribution models. Environ. Model. Softw.25, 1630-1639.
2. Aguilera, P.A., Fernández, A., Fernández, R., Rumí, R., Salmerón, A., 2011. Bayesiannetworks in environmental modelling. Environ. Model. Softw. 26, 1376-1388.
3. Brandtberg, T., 2007. Classifying individual tree species under leaf-off and leaf-on conditions using airborne lidar. ISPRS-J. Photogramm. Remote Sens. 61,325-340.
4. Brandtberg, T., Walter, F., 1998. Automated delineation of individual tree crowns inhigh spatial resolution aerial images by multiple-scale analysis. Mach. Vis. Appl.11, 64-73.
5. Bressan, G.M., Oliveira, V.A., Hruschka Jr., E.R., Nicoletti, M.C., 2009. Using Bayesiannetworks with rule extraction to infer the risk of weed infestation in a corn-crop.Eng. Appl. Artif. Intell. 22, 579-592.
6. Chen, Q., Baldocchi, D., Gong, P., Kelly, M., 2006. Isolating individual trees in a savannawoodland using small footprint lidar data. Photogramm. Eng. Remote Sens. 72,923-932.
7. Cheng, H., Wang, R., 2010. Semantic modeling of natural scenes based on contextualBayesian networks. Pattern Recognit. 43, 4042-4054.
8. Chubey, M.S., Franklin, S.E., Wulder, M.A., 2006. Object-based analysis of Ikonos-2 imagery for extraction of forest inventory parameters. Photogramm. Eng.Remote Sens. 72, 383-394.
9. Cordero-Sancho, S., Sader, S.A., 2007. Spectral analysis and classification accuracyof coffee crops using Landsat and a topographic-environmental model. Int. J.Remote Sens. 28, 1577-1593.
10. Cordingley, J., 2009. Soil Fertility Survey of Rwanda for Developing Lime and Fertil-izer Recommendations for Coffee. OCIR, Cafe, Kigali, pp. 62.
11. Doxani, G., Karantzalos, K., Strati, M.T., 2012. Monitoring urban changes based onscale-space filtering and object-oriented classification. Int. J. Appl. Earth Obs.Geoinf. 15, 38-48.
12. Forster, D., Buehler, Y., Kellenberger, T.W., 2009. Mapping urban and peri-urbanagriculture using high spatial resolution satellite data. J. Appl. Remote Sens. 3.
13. Gambelli, D., Bruschi, V., 2010. A Bayesian network to predict the probability oforganic farms' exit from the sector: a case study from Marche, Italy. Comput.Electron. Agric. 71, 22-31.
14. Gomez, C., Mangeas, M., Petit, M., Corbane, C., Hamon, P., Hamon, S., De Kochko,A., Le Pierres, D., Poncet, V., Despinoy, M., 2010. Use of high-resolution satelliteimagery in an integrated model to predict the distribution of shade coffee treehybrid zones. Remote Sens. Environ. 114, 2731-2744.
15. Gong, P., Sheng, Y., Biging, G.S., 2002. 3D model-based tree measurement from high-resolution aerial imagery. Photogramm. Eng. Remote Sens. 68, 1203-1212.
16. Gougeon, F.A., Leckie, D.G., 2006. The individual tree crown approach applied toIkonos images of a coniferous plantation area. Photogramm. Eng. Remote Sens.72, 1287-1297.
17. Huhndorf, M.H., Kerbis Peterhans, J.C., Loew, S.S., 2007. Comparative phylogeogra-phy of three endemic rodents from the Albertine Rift, east central Africa. Mol.Ecol. 16, 663-674.
18. Johansen, K., Coops, N.C., Gergel, S.E., Stange, Y., 2007. Application of high spatial res-olution satellite imagery for riparian and forest ecosystem classification. RemoteSens. Environ. 110, 29-44.
19. Johansen, K., Phinn, S., Witte, C., Philip, S., Newton, L., 2009. Mapping banana planta-tions from object-oriented classification of SPOT-5 imagery. Photogramm. Eng.Remote Sens. 75, 1069-1081.
20. Kim, S.-R., Kwak, D.-A., oLee, W.-K., Son, Y., Bae, S.-W., Kim, C., Yoo, S., 2010. Esti-mation of carbon storage based on individual tree detection in Pinus densiflorastands using a fusion of aerial photography and LiDAR data. Sci. China Life Sci.53, 885-897.
21. Kok, K., Veldkamp, T., 2011. Scale and governance: conceptual considerations andpractical implications. Ecol. Soc. 16.
22. Kumar, R., Silva, L., 1974. Statistical separability of spectral classes of blighted corn.Remote Sens. Environ. 3, 109-115.
23. Langford, M., Bell, W., 1997. Land cover mapping in a tropical hillsides environment:a case study in the Cauca region of Colombia. Int. J. Remote Sens. 18, 1289-1306.
24. Loveridge, S., Nyarwaya, J.B., Shingiro, E., 2003. In: FSRP (Ed.), Decaffeinated? Situ-ation, Trends, and Prospects for Coffee Production in Rwanda. Kigali, Rwanda,pp. 9-81.
25. Mello, M.P., Rudorff, B.F.T., Adami, M., Rizzi, R., Aguiar, D.A., Gusso, A., Fonseca, L.M.G., 2010. IEEE. A Simplified Bayesian Network to Map Soybean Plantations. IEEE,New York.
26. Moreira, M.A., Adam, M., Rudorff, B.F.T., 2004. Spectral and temporal behavior anal-ysis of coffee crop in Landsat images. Pesqui. Agropecuaria Bras. 39, 223-231.
27. Moreira, M.A., Rudorff, B.F.T., Barros, M.A., De Faria, V.G.C., Adami, M., 2010. Geotech-nologies to map coffee fields in the states of Minas Gerais and Sao Paulo.Engenharia Agricola 30, 1123-1135.
28. Nsengiyumva, F., 2009. In: OCIR-CAFE/NAEB (Ed.), Rwanda National Coffee Census.Kigali, Rwanda, p. 76.
29. Ortega-Huerta, M.A., Komar, O., Price, K.P., Ventura, H.J., 2012. Mapping coffee plan-tations with Landsat imagery: an example from El Salvador. Int. J. Remote Sens.33, 220-242.
30. Park, M.-H., Stenstrom, M.K., 2006. Using satellite imagery for stormwater pollutionmanagement with Bayesian networks. Water Res. 40, 3429-3438.
31. Pouliot, D.A., King, D.J., Bell, F.W., Pitt, D.G., 2002. Automated tree crown detectionand delineation in high-resolution digital camera imagery of coniferous forestregeneration. Remote Sens. Environ. 82, 322-334.
32. Qu, Y., Wang, J., Wan, H., Li, X., Zhou, G., 2008. A Bayesian network algorithm forretrieving the characterization of land surface vegetation. Remote Sens. Environ.112, 613-622.
33. Schilling, M., Mukashema, A., Westinga, E., Lasry, F., Mlotha, J., Iraguha, G., 2007.Forest Mapping of Rwanda. In: Synthesis, Centre for Geographic InformationSystems and Remote Sensing (CGIS). National University of Rwanda (NUR),Huye, pp. 146.
34. Swedesurvey, 2010. Report for Production of ortho photo in Rwanda. In: RwandaNational Land Use and Development Master Plan. Rwanda National Land Centre,Ministry of Natural Resources, Kigali-RWANDA, pp. 9.
35. Trabaquini, K., Miglioranza, E., de Franca, V., Neto, O.C.P., 2011. Characterization ofcoffee crops using techniques of geoprocessing and remote sensing in the cityof Umuarama - PR. Ciencia E Agrotecnologia 35, 35-44.
36. Veldkamp, A., Kok, K., De Koning, G.H.J., Schoorl, J.M., Sonneveld, M.P.W., Verburg,P.H., 2001. Multi-scale system approaches in agronomic research at the land-scape level. Soil Tillage Res. 58, 129-140.
37. Verdoodt, A., Van Ranst, E., 2006. Environmental assessment tools for multi-scaleland resources information systems - a case study of Rwanda. Agric. Ecosyst.Environ. 114, 170-184.
38. Verwimp, P., 2003. The political economy of coffee, dictatorship, and genocide. Eur.J. Pol. Econ. 19, 161-181.
39. Wang, L., Gong, P., Biging, G.S., 2004. Individual tree-crown delineation and tree-top detection high-spatial-resolution aerial imagery. Photogramm. Eng. RemoteSens. 70, 351-357.
40. Westinga, E., Mukashema, A., van Gils, H., 2013. A comparison of fine resolutioncensus and image-based national forest inventories: a case study of Rwanda.Forestry 86, 453-461.
41. Wulder, M., Niemann, K.O., Goodenough, D.G., 2000. Local maximum filtering for theextraction of tree locations and basal area from high spatial resolution imagery.Remote Sens. Environ. 73, 103-114.