Mapping Rice Cropping Systems in Data-Scarce Regions Using NDVI Time-Series and Dynamic Time Warping Clustering: A Case Study of Maliana, Timor-Leste
Source abstract
Abstract
Mapping of rice-cropping regimes is crucial for effective irrigation planning and yield monitoring, particularly in data-scarce regions. We analyzed 48 months of 3 m PlanetScope NDVI data, aggregated to a 25 m hexagonal grid, and used Dynamic Time Warping Clustering to segment phenological patterns. Internal validation consistently identified two main clusters, indicating two dominant seasonality modes. Cluster 1 exhibited a higher mean NDVI, fewer low-canopy months, more vigorous growth periods, more peaks, and greater annual cycling, which suggests irrigated double cropping. Cluster 2 exhibited prolonged low NDVI values and a greater amplitude, consistent with single-rainfed systems. The rain–NDVI analysis supported these findings: Cluster 1 responded modestly to rainfall, whereas Cluster 2 exhibited a stronger and delayed response. Independent spatial checks confirmed these classifications. Off-season greenness, measured as NDVI above 0.50 from July to November, was concentrated near main and secondary canals and decreased with distance from intake points. This workflow combines DTW clustering with rainfall lag and off-season greenness analysis, effectively distinguishing between irrigated and rain-fed regimes using satellite time series. These findings are considered indicative rather than definitive, providing an assessment of cropping systems in Timor-Leste and demonstrating that DTW-based NDVI clustering offers a scalable approach in data-scarce regions.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Remote Sensing in Agriculture · Climate change impacts on agriculture · Rice Cultivation and Yield Improvement
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Graduate School of Science and Technology for Innovation, Yamaguchi University, 2-16-1, Ube 755-8611, Yamaguchi, Japan
Center for Research and Application of Satellite Remote Sensing, Yamaguchi University, 2-16-1, Tokiwadai, Ube 755-8611, Yamaguchi, Japan
References (67)
Show source-provided references
1. Rice: Importance for Global Nutrition10.3177/jnsv.65.S2 ↗
2. FAO (2025, August 01). Chapter 3—Rice in Human Nutrition. Available online: https://www.fao.org/4/x6905e/x6905e04.htm.
3. USDA ERS (2025, August 01). Rice Sector at a Glance, Available online: https://www.ers.usda.gov/topics/crops/rice/rice-sector-at-a-glance.
4. Barker, R., Herdt, R.W., and Rose, B. (2000). The Impact of Technological Change on Income Distribution in Developing Countries: A Case Study on the Rice Sector in Bangladesh. The Asian Rice Economy in Transition, CABI Publishing.
5. Rice in the Global Food Supply
6. FAO (2025, August 02). GIEWS Country Brief: Timor-Leste. Available online: https://www.fao.org/giews/countrybrief/country.jsp?code=TLS.
7. Japan International Cooperation Agency (JICA) (2025, November 20). Joint Terminal Evaluation Report on the Project for Increasing Farmers Households’ Income Through Strengthening Domestic Rice Production in Timor-Leste, Available online: https://openjicareport.jica.go.jp/pdf/1000051826.pdf.
8. World Bank (2023). Timor-Leste Economic Report: Charting a New Path for Growth, World Bank.
9. da Costa, H., Piggin, C., Cruz, J., and Fox, J.J. (2003). Drawing from the Past to Prepare for the Future: Responding to the Challenges of Food Security in East Timor, Agriculture: New Directions for a New Nation—East Timor (Timor-Leste), ACIAR Proceedings No. 113.
10. FAO (2019). Evaluation of FAO’s Contribution to the Democratic Republic of Timor-Leste—2015–2018, FAO.
11. World Bank (2023). Timor-Leste Economic Report: Ways to Harvest Prosperity, World Bank. Available online: https://documents1.worldbank.org/curated/en/099082423184080415/pdf/P17968900c0be2080af39081ae63bb6cf9.pdf.
12. Grain Yield of Rice, Corn, and Sorghum to Low External Input Agriculture Practices in Maliana, Bobonaro, Timor-Leste
13. Monitoring Vegetation Phenology Using MODIS10.1016/S0034-4257(02)00135-9 ↗
14. Zhang, X., Friedl, M.A., and Schaaf, C.B. (2006). Global Vegetation Phenology from Moderate Resolution Imaging Spectroradiometer (MODIS): Evaluation of Global Patterns and Comparison with In Situ Measurements. J. Geophys. Res. Biogeosci., 111.10.1029/2006JG000217 ↗
15. Measuring Phenological Variability from Satellite Imagery10.2307/3235884 ↗
16. The Normalized Difference Vegetation Index (NDVI) of the Zat Valley, Marrakech: Comparison and Dynamics10.1016/j.heliyon.2022.e12204 ↗
17. Field Validation of NDVI to Identify Crop Phenological Signatures10.1007/s11119-024-10165-6 ↗
18. Rectangular and Hexagonal Grids Used for Observation, Experiment and Simulation in Ecology10.1016/j.ecolmodel.2007.03.041 ↗
19. Guan, X., Huang, C., Liu, G., Meng, X., and Liu, Q. (2016). Mapping Rice Cropping Systems in Vietnam Using an NDVI-Based Time-Series Similarity Measurement Based on DTW Distance. Remote Sens., 8.10.3390/rs8010019 ↗
20. Silhouettes: A Graphical Aid to the Interpretation and Validation of Cluster Analysis10.1016/0377-0427(87)90125-7 ↗
21. Hämäläinen, J., Jauhiainen, S., and Kärkkäinen, T. (2017). Comparison of Internal Clustering Validation Indices for Prototype-Based Clustering. Algorithms, 10.10.3390/a10030105 ↗
22. Internal versus External Cluster Validation Indexes
23. Assessing Vegetation Response to Drought in the Northern Great Plains Using Vegetation and Drought Indices10.1016/S0034-4257(03)00174-3 ↗
24. Chen, Z., Wang, W., and Fu, J. (2020). Vegetation Response to Precipitation Anomalies under Different Climatic and Biogeographical Conditions in China. Sci. Rep., 10.10.1038/s41598-020-57910-1 ↗
25. Discrimination of Irrigated and Rainfed Rice in a Tropical Agricultural System Using SPOT VEGETATION NDVI and Rainfall Data10.1080/01431160500104335 ↗
26. The Relationship between Threshold-Based and Inflexion-Based Approaches for Extraction of Land Surface Phenology10.1016/j.rse.2017.07.020 ↗
27. Autoridade Munisípiu Bobonaro (2025, August 02). Agriculture Statistics Dashboard, Available online: https://bobonaro.gov.tl/en/dashboard/.
28. Correia, V.P., and Sarmento, D.R. (2020). Baseline Study on the Identification of Local Products in Timor-Leste that Have Potential for Export Market and to Attract Private Investments in Agriculture Sector, National Center for Scientific Research (CNIC) UNTL.
29. FAO (2021). Special Report—2021 FAO Crop and Food Supply Assessment Mission (CFSAM) to the Democratic Republic of Timor-Leste, FAO.
30. FAO (2011). AQUASTAT Country Profile—Timor-Leste, Food and Agriculture Organization of the United Nations. Available online: https://openknowledge.fao.org/server/api/core/bitstreams/2169f881-507c-4606-9181-30d66ad2941b/content.
31. National Directorate for Agriculture and Horticulture, Ministry of Agriculture and Fisheries, and The Democratic Republic of Timor-Leste (2015). Project for Agriculture Master Plan and Irrigation Development Plan: Final Report, Japan International Cooperation Agency (JICA), Sanyu Consultants Inc.
32. Huuborg, R., and McCabe, M.F. (2016). High-Resolution NDVI from Planet’s Constellation of Earth Observing Nano-Satellites: A New Data Source for Precision Agriculture. Remote Sens., 8.10.3390/rs8090768 ↗
33. Significant Remote Sensing Vegetation Indices: A Review of Developments and Applications10.1155/2017/1353691 ↗
34. Observation of flooding and rice transplanting of paddy rice fields at the site to landscape scales in China using VEGETATION sensor data
35. Shi, Y., Huang, W., Ye, H., Ruan, C., Xing, N., Geng, Y., Dong, Y., and Peng, D. (2018). Partial Least Square Discriminant Analysis Based on Normalized Two-Stage Vegetation Indices for Mapping Damage from Rice Diseases Using PlanetScope Datasets. Sensors, 18.10.3390/s18061901 ↗
36. Esri (2025, October 01). Why Hexagons? ArcGIS Pro Documentation. Available online: https://pro.arcgis.com/en/pro-app/3.4/tool-reference/spatial-statistics/h-whyhexagons.htm.
37. The Dynamic-Time-Warping-based k-means++ clustering and its application in phenoregion delineation10.1080/01431161.2017.1286055 ↗
38. A global averaging method for dynamic time warping, with applications to clustering10.1016/j.patcog.2010.09.013 ↗
39. Tslearn, a machine learning toolkit for time series data
40. Constrained Distance-Based Clustering for Satellite Image Time-Series10.1109/JSTARS.2019.2950406 ↗
41. Dynamic programming algorithm optimization for spoken word recognition10.1109/TASSP.1978.1163055 ↗
42. Mure, S., Grenier, T., Guttmann, C.R.G., and Benoit-Cattin, H. (2016, January 20–25). Unsupervised time-series clustering of distorted and asynchronous temporal patterns. Proceedings of the 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shanghai, China.10.1109/ICASSP.2016.7471879 ↗
43. Cuturi, M., and Blondel, M. (2017). Soft-DTW: A differentiable loss function for time-series. arXiv.
44. tslearn Developers (2025, October 01). TimeSeriesKMeans—Tslearn 0.6.4 Documentation. Available online: https://tslearn.readthedocs.io/en/stable/gen_modules/clustering/tslearn.clustering.TimeSeriesKMeans.html.
45. tslearn Developers (2025, October 01). TimeSeriesScalerMinMax—Tslearn 0.6.4 Documentation. Available online: https://tslearn.readthedocs.io/en/stable/gen_modules/preprocessing/tslearn.preprocessing.TimeSeriesScalerMinMax.html.
46. (2025, August 01). Elbow Method for Optimal Value of K in KMeans. Available online: https://www.geeksforgeeks.org/machine-learning/elbow-method-for-optimal-value-of-k-in-kmeans/.
47. A quantitative discriminant method of elbow point for the optimal number of clusters in clustering algorithm10.1186/s13638-021-01910-w ↗
48. Umaragono, E., Suseno, J.E., and Gunawan, V.G.S.K. (2019, January 24–25). K-Means Clustering Optimization using the Elbow Method and Early Centroid Determination Based-on Mean and Median. Proceedings of the International Conferences on Information System and Technology (CONRIST), Yogyakarta, Indonesia.10.5220/0009908402340240 ↗
49. An efficient method to improve the clustering performance for high dimensional data by Principal Component Analysis and modified K-means
50. Marín Celestino, A.E., Martínez Cruz, D.A., Otazo Sánchez, E.M., Gavi Reyes, F., and Vásquez Soto, D. (2018). Groundwater quality assessment: An improved approach to K-Means clustering, Principal Component Analysis and spatial analysis: A case study. Water, 10.10.3390/w10040437 ↗
51. Awong, L.E.E., and Zielinska, T. (2023). Comparative Analysis of the Clustering Quality in Self-Organizing Maps for Human Posture Classification. Sensors, 23.10.3390/s23187925 ↗
52. A Cluster Separation Measure10.1109/TPAMI.1979.4766909 ↗
53. A dendrite method for cluster analysis
54. An improved index for clustering validation based on Silhouette index and Calinski–Harabasz index10.1088/1757-899X/569/5/052024 ↗
55. Box, G.E.P., Jenkins, G.M., Reinsel, G.C., and Ljung, G.M. (2015). Time Series Analysis: Forecasting and Control, Wiley. [5th ed.].
56. Chatfield, C. (2003). The Analysis of Time Series: An Introduction, Chapman and Hall/CRC. [6th ed.].
57. Response of vegetation to drought time-scales across global land biomes
58. Time-lag effects of global vegetation responses to climate change10.1111/gcb.12945 ↗
59. Robust locally weighted regression and smoothing scatterplots10.1080/01621459.1979.10481038 ↗
60. Bayesian stock assessment using a state–space implementation of the delay difference model
61. Tao, J., Zhang, X., Liu, Y., Jiang, Q., and Zhou, Y. (2023). Estimating agricultural cropping intensity using a new temporal mixture analysis method from time series MODIS. Remote Sens., 15.10.3390/rs15194712 ↗
62. Zhu, A.-X., Zhao, F.-H., Pan, H.-B., and Liu, J.-Z. (2021). Mapping rice paddy distribution using remote sensing by coupling deep learning with phenological characteristics. Remote Sens., 13.10.3390/rs13071360 ↗
63. Recent trends in vegetation dynamics in the African Sahel and their relationship to climate10.1016/j.gloenvcha.2005.08.004 ↗
64. Long-term vegetation monitoring with NDVI in a diverse semi-arid setting, central New Mexico, USA10.1016/j.jaridenv.2003.07.001 ↗
65. A statistical study of NDVI sensitivity to seasonal and interannual rainfall variations in Southern Africa10.1080/014311698214343 ↗
66. Wang, S., and Fan, F. (2021). Analysis of the response of long-term vegetation dynamics to climate variability using the pruned exact linear time (PELT) method and disturbance lag model (DLM) based on remote sensing data: A case study in Guangdong Province (China). Remote Sens., 13.10.3390/rs13101873 ↗
67. Japan International Cooperation Agency (JICA), and Sanyu Consultants Inc (2007). Implementation Review Study Report on the Project for Rehabilitation and Improvement of Maliana I Irrigation System in the Democratic Republic of Timor-Leste.