Lowland Rice Mapping in Sédhiou Region (Senegal) Using Sentinel 1 and Sentinel 2 Data and Random Forest
Abstract
:1. Introduction
- What are the NDVI and backscatter temporal profiles of the land cover classes present in South Senegal’s lowland areas?
- What is the individual relative importance of selected input predictors for the classification task?
- Is the combination of radar and optical imagery able to outperform a classification based on single-sensor inputs?
2. Materials
2.1. Study Area
2.2. Data Used in This Study
2.2.1. Sentinel 1 and Sentinel 2 Data
2.2.2. Ground Validation Data
2.2.3. Lowland Area Mask
3. Methods
3.1. Pre-Processing of S1 and S2 Imagery
3.2. Processing of S1 and S2 Imagery
3.3. Image Classification by RF
3.3.1. Computation and Optimal Selection of Predictors
3.3.2. Application of RF Classifier and Accuracy Assessment
3.4. Statistical Estimation of Rice Area
4. Results
4.1. Temporal NDVI and Backscatter Land Cover Patterns
4.2. Importance of Predictors
4.3. Classification Results and Accuracy Assessment
4.4. Assessment of Classification Accuracies with Different Dataset Combinations
4.5. Statistical Estimation of Rice Area
5. Discussion
6. Conclusions
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
References
- Ahmadi, N.; Bouman, B. Riz et rizicultures, enjeux économiques, écologiques et scientifiques. Cahiers Agric. 2013, 2222, 333–335. [Google Scholar] [CrossRef]
- Mendez Del Villar, P.M.; Bauer, J.M. Le riz en Afrique de l’Ouest: Dynamiques, politiques et perspectives. Cah. Agric. 2013, 2222, 336–344. [Google Scholar] [CrossRef]
- Maclean, J.; Hardy, B.; Hettel, G. Rice Almanac: Source Book for One of the Most Important Economic Activities on Earth, 3rd ed.; IRRI: Manila, Philippines, 2013; pp. 216–217. ISBN 0-85199-636-1. [Google Scholar]
- FAOSTAT Statistical Database; FAO (Food and Agriculture Organization of the United Nations): Rome, Italy, 2020; Available online: http://www.fao.org/faostat/en/#home (accessed on 21 June 2020).
- Mendez Del Villar, P.; Bauer, J.M.; Maiga, A.; Ibrahim, L. Crise Rizicole, Évolution des Marchés et Sécurité Alimentaire en AFRIQUE de l’Ouest; Appraisal Report; CIRAD: Montpellier, France, 2011. [Google Scholar]
- Seck, P.A.; Togola, A.; Touré, A.; Diagne, A. Propositions pour une optimisation des performances de la riziculture en Afrique de l’Ouest. Cah. Agric. 2013, 2222, 361–368. [Google Scholar] [CrossRef]
- Gueye, A.A. Étude bibliographique sur la filière riz au Sénégal. Rapport final. Bamako (Mali): Observatoire national du Riz au Sénégal (ONRS), Atelier régional du PRIAF-RIZ (2004). Available online: http://hubrural.org/IMG/pdf/senegal-etude-biblio-filiere-riz.pdf (accessed on 21 June 2020).
- Programme National D’autosuffisance en Riz (PNAR). Ministère de l’Agriculture. 2009. Available online: https://www.ipar.sn/IMG/pdf/2009_Prog_Nat_Autosufisance_Riz.pdf (accessed on 21 June 2020).
- Mendez Del Villar, E. Rapport de Mission. Le Riz Pluvial en Casamance et Bassin Arachidier; CIRAD: Montpellier, France, 2019. [Google Scholar]
- Mosleh, M.K.; Hassan, Q.K.; Chowdhury, E.H. Application of remote sensors in mapping rice area and forecasting its production: A review. Sensors 2015, 15, 769–791. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Dong, J.; Xiao, X. Evolution of regional to global paddy rice mapping methods: A review. ISPRS J. Photogramm. Remote Sens. 2016, 119, 214–227. [Google Scholar] [CrossRef] [Green Version]
- Kuenzer, C.; Knauer, K. Remote sensing of rice crop areas. Int. J. Remote Sens. 2013, 34, 2101–2139. [Google Scholar] [CrossRef]
- Turner, M.D.; Congalton, R.G. Classification of multi-temporal SPOT-XS satellite data for mapping rice fields on a West African floodplain. Int. J. Remote Sens. 1998, 19, 21–41. [Google Scholar] [CrossRef]
- Busetto, L.; Zwart, S.J.; Boschetti, M. Analysing spatial–temporal changes in rice cultivation practices in the Senegal River Valley using MODIS time-series and the PhenoRice algorithm. Int. J. Appl. Earth Obs. Geoinf. 2019, 75, 15–28. [Google Scholar] [CrossRef]
- Bouvet, A.; Le Toan, T. Use of ENVISAT/ASAR wide-swath data for timely rice fields mapping in the Mekong River Delta. Remote Sens. Environ. 2011, 115115, 1090–1101. [Google Scholar] [CrossRef] [Green Version]
- Stroppiana, D.; Boschetti, M.; Azar, R.; Barbieri, M.; Collivignarelli, F.; Gatti, L.; Fontanelli, G.; Busetto, L.; Holecz, F. In-season early mapping of rice area and flooding dynamics from optical and SAR satellite data. Eur. J. Remote Sens. 2019, 52, 206–220. [Google Scholar] [CrossRef] [Green Version]
- Breiman, L. Random Forest. Mach. Learn. 2001, 45, 5–32. [Google Scholar]
- Hao, P.; Zhan, Y.; Wang, L.; Niu, Z.; Shakir, M. Feature selection of time series MODIS data for early crop classification using random forest: A case study in Kansas, USA. Remote Sens. 2015, 7, 5347–5369. [Google Scholar] [CrossRef] [Green Version]
- Li, Q.; Wang, C.; Zhang, B.; Lu, L. Object-based crop classification with Landsat-MODIS enhanced time-series data. Remote Sens. 2015, 7, 16091–16107. [Google Scholar] [CrossRef] [Green Version]
- Novelli, A.; Aguilar, M.A.; Nemmaoui, A.; Aguilar, F.J.; Tarantino, E. Performance evaluation of object based greenhouse detection from Sentinel-2 MSI and Landsat 8 OLI data: A case study from Almería (Spain). Int. J. Appl. Earth Obs. Geoinf. 2016, 52, 403–411. [Google Scholar] [CrossRef] [Green Version]
- Pelletier, C.; Valero, S.; Inglada, J.; Champion, N.; Dedieu, G. Assessing the robustness of Random Forests to map land cover with high resolution satellite image time series over large areas. Remote Sens. Environ. 2016, 187, 156–168. [Google Scholar] [CrossRef]
- Jin, X.; Li, Z.; Yang, G.; Yang, H.; Feng, H.; Xu, X.; Wang, J.; Li, X.; Luo, J. Winter wheat yield estimation based on multi-source medium resolution optical and radar imaging data and the AquaCrop model using the particle swarm optimization algorithm. ISPRS J. Photogramm. Remote Sens. 2017, 126, 24–37. [Google Scholar] [CrossRef]
- Van Tricht, K.; Gobin, A.; Gilliams, S.; Piccard, I. Synergistic use of radar sentinel-1 and optical sentinel-2 imagery for crop mapping: A case study for Belgium. Remote Sens. 2018, 10, 1642. [Google Scholar] [CrossRef] [Green Version]
- Veloso, A.; Mermoz, S.; Bouvet, A.; le Toan, T.; Planells, M.; Dejoux, J.F.; Ceschia, E. Understanding the temporal behavior of crops using Sentinel-1 and Sentinel-2-like data for agricultural applications. Remote Sens. Environ. 2017, 199, 415–426. [Google Scholar] [CrossRef]
- Hakdaoui, S.; Emran, A.; Pradhan, B.; Lee, C.W.; Nguemhe Fils, S.C. A collaborative change detection approach on multi-sensor spatial imagery for desert wetland monitoring after a flash flood in southern Morocco. Remote Sens. 2019, 11, 1042. [Google Scholar] [CrossRef] [Green Version]
- Cai, Y.; Lin, H.; Zhang, M. Mapping paddy rice by the object-based random forest method using time series Sentinel-1/Sentinel-2 data. Adv. Space Res. 2019, 64, 2233–2244. [Google Scholar] [CrossRef]
- Manzelli, M.; Fiorillo, E.; Bacci, M.; Tarchiani, V. Lowland rice production in southern Senegal (Middle Casamance): Challenges and prospects for sustaining their restoration and development. Cahiers Agric. 2015, 24, 301–312. [Google Scholar] [CrossRef]
- Manzelli, M.; Seppoloni, I.; Zucchini, E.; Bacci, M.; Fiorillo, E.; Tarchiani, V. La riziculture traditionnelle de bas-fond en Moyenne Casamance dans un contexte de changements globaux: Enjeux et perspectives. In Eaux et Sociétés Face au Changement Climatique Dans le Bassin de la Casamance; L’Harmattan: Paris, France, 2015. [Google Scholar]
- Manzelli, M.; Bacci, M.; Fiorillo, E.; Tarchiani, V. Diagnostique de la Riziculture de Bas-fonds Dans la Région de Sédhiou. Available online: https://www.papsen.org/data/files/PAPSEN_2_VALLEES_0913.pdf (accessed on 5 June 2020).
- Muller-Wilm, U.; Louis, J.; Richter, R.; Gascon, F.; Niezette, M. Sentinel-2 level 2A prototype processor: Architecture, algorithms and first results. In Proceedings of the ESA Living Planet Symposium, Edinburgh, UK, 9–13 September 2013; pp. 9–13. [Google Scholar]
- Savitzky, A.; Golay, M.J. Smoothing and differentiation of data by simplified least squares procedures. Anal. Chem. 1964, 3636, 1627–1639. [Google Scholar] [CrossRef]
- Simard, M.; Riel, B.V.; Denbina, M.; Hensley, S. Radiometric correction of airborne radar images over forested terrain with topography. IEEE Trans. Geosci. Remote Sens. 2016, 54, 4488–4500. [Google Scholar] [CrossRef]
- Torbick, N.; Chowdhury, D.; Salas, W.; Qi, J. Monitoring Rice Agriculture across Myanmar Using Time Series Sentinel-1 Assisted by Landsat-8 and PALSAR-2. Remote Sens. 2017, 9, 119. [Google Scholar] [CrossRef] [Green Version]
- Murugan, D.; Singh, D. Development of an approach for monitoring sugarcane harvested and non-harvested conditions using time series Sentinel-1 data. In Proceedings of the IGARSS 2018–2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain, 22–27 July 2018; IEEE: Piscataway, NJ, USA, 2018; pp. 5308–5311. [Google Scholar]
- Phung, H.P.; Nguyen, L.D.; Thong, N.H.; Thuy, L.T.; Apan, A.A. Monitoring rice growth status in the Mekong Delta, Vietnam using multitemporal Sentinel-1 data. J. Appl. Remote Sens. 2020, 14, 014518. [Google Scholar] [CrossRef] [Green Version]
- Rouse, J.W.; Haas, R.H.; Schell, J.A.; Deering, D.W.; Harlan, J.C. Monitoring the Vernal Advancements and Retrogradation (Green Wave Effect) of Natural Vegetation; Final Report; NASA/GSFC: Greenbelt, MD, USA, 1974; pp. 371–385. [Google Scholar]
- Xiao, X.; He, L.; Salas, W.; Li, C.; Moore Iii, B.; Zhao, R.; Frolking, S.; Boles, S. Quantitative relationships between field-measured leaf area index and vegetation index derived from VEGETATION images for paddy rice fields. Int. J. Remote Sens. 2002, 23, 3595–3604. [Google Scholar] [CrossRef]
- Guan, X.; Huang, C.; Liu, G.; Meng, X.; Liu, Q. Mapping rice cropping systems in Vietnam using an NDVI-based time-series similarity measurement based on DTW distance. Remote Sens. 2016, 8, 19. [Google Scholar] [CrossRef] [Green Version]
- Escadafal, R.; Bohbot, H.; Mégier, J. Changes in Arid Mediterranean Ecosystems on the Long Term through Earth Observation (CAMELEO); Final Report of EU contract IC18-CT97-0155; Space Applications Institute, JRC: Ispra, Italy, 2001. [Google Scholar]
- Maselli, F.; Barbati, A.; Chiesi, M.; Chirici, G.; Corona, P. Use of remotely sensed and ancillary data for estimating forest gross primary productivity in Italy. Remote Sens. Environ. 2006, 100, 563–575. [Google Scholar] [CrossRef] [Green Version]
- Belgiu, M.; Csillik, O. Sentinel-2 cropland mapping using pixel-based and object-based time-weighted dynamic time warping analysis. Remote Sens. Environ. 2018, 204, 509–523. [Google Scholar] [CrossRef]
- Torbick, N.; Huang, X.; Ziniti, B.; Johnson, D.; Masek, J.; Reba, M. Fusion of moderate resolution earth observations for operational crop type mapping. Remote Sens. 2018, 10, 1058. [Google Scholar] [CrossRef] [Green Version]
- Son, N.T.; Chen, C.F.; Chen, C.R.; Minh, V.Q. Assessment of Sentinel-1A data for rice crop classification using random forests and support vector machines. Geocarto Int. 2018, 33, 587–601. [Google Scholar] [CrossRef]
- Hastie, T.; Tibshirani, R.; Friedman, J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction; Springer Science: Berlin/Heidelberg, Germany; Business Media: Berlin/Heidelberg, Germany, 2009. [Google Scholar]
- Ghazaryan, G.; Dubovyk, O.; Löw, F.; Lavreniuk, M.; Kolotii, A.; Schellberg, J.; Kussul, N. A rulebased approach for crop identification using multi-temporal and multi-sensor phenological metrics. Eur. J. Remote Sens. 2018, 51, 511–524. [Google Scholar] [CrossRef]
- Lu, D. The potential and challenge of remote sensing-based biomass estimation. Int. J. Remote Sens. 2006, 27, 1297–1328. [Google Scholar] [CrossRef]
- Deng, H.; Runger, G. Gene selection with guided regularized random forest. Pattern Recognit. 2012, 46, 3483–3489. [Google Scholar] [CrossRef] [Green Version]
- Izquierdo-Verdiguier, E.; Zurita-Milla, R.; Rolf, A. On the use of guided regularized random forests to identify crops in smallholder farm fields. In Proceedings of the 2017 9th International Workshop on the Analysis of Multitemporal Remote Sensing Images 9th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp), Bruges, Belgium, 27–29 June 2017; pp. 1–3. [Google Scholar] [CrossRef]
- Izquierdo-Verdiguier, E.; Zurita-Milla, R. Use of guided regularized random forest for biophysical parameter retrieval. In Proceedings of the IGARSS 2018–2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain, 22–27 July 2018; IEEE: Piscataway, NJ, USA, 2018; pp. 5776–5779. [Google Scholar]
- Sánchez-Ruiz, S.; Moreno-Martínez, Á.; Izquierdo-Verdiguier, E.; Chiesi, M.; Maselli, F.; Gilabert, M.A. Growing stock volume from multi-temporal landsat imagery through google earth engine. Int. J. Appl. Earth Obs. Geoinf. 2019, 83, 101913. [Google Scholar] [CrossRef]
- Millard, K.; Richardson, M. On the importance of training data sample selection in random forest image classification: A case study in peatland ecosystem mapping. Remote Sens. 2015, 7, 8489. [Google Scholar] [CrossRef] [Green Version]
- Cohen, J. A coefficient of agreement for nominal scales. Educ. Psychol. Meas. 1960, 20, 37–46. [Google Scholar] [CrossRef]
- Samasse, K.; Hanan, N.P.; Anchang, J.Y.; Diallo, Y. A high-resolution cropland map for the West African Sahel based on high-density training data, Google Earth Engine, and locally optimized machine learning. Remote Sens. 2020, 12, 1436. [Google Scholar] [CrossRef]
- Xiao, X.; Boles, S.; Liu, J.; Zhuang, D.; Frolking, S.; Li, C.; Salas, W.; Moore III, B. Mapping paddy rice agriculture in southern China using multi-temporal MODIS images. Remote Sens. Environ. 2005, 95, 480–492. [Google Scholar] [CrossRef]
- Xiao, X.; Boles, S.; Frolking, S.; Li, C.; Babu, J.Y.; Salas, W.; Moore III, B. Mapping paddy rice agriculture in South and Southeast Asia using multi-temporal MODIS images. Remote Sens. Environ. 2006, 100, 95–113. [Google Scholar] [CrossRef]
- Boschetti, M.; Busetto, L.; Manfron, G.; Laborte, A.; Asilo, S.; Pazhanivelan, S.; Nelson, A. PhenoRice: A method for automatic extraction of spatio-temporal information on rice crops using satellite data time series. Remote Sens. Environ. 2017, 194, 347–365. [Google Scholar] [CrossRef] [Green Version]
- Yang, C.M.; Cheng, C.H. Spectral characteristics of rice plants infested by brown planthoppers. Proc. Natl. Sci. Counc. Repub. China. B 2001, 25, 180–186. [Google Scholar] [PubMed]
- Yang, C.M.; Cheng, C.H.; Chen, R.K. Changes in spectral characteristics of rice canopy infested with Brown Planthopper and Leaffolder. Crop Sci. 2007, 47, 329–335. [Google Scholar] [CrossRef]
- Nguyen, D.B.; Wagner, W. European rice cropland mapping with Sentinel-1 data: The mediterranean region case study. Water 2017, 9, 392. [Google Scholar] [CrossRef]
Class | 2017 | 2018 | 2019 | |||
---|---|---|---|---|---|---|
Train | Test | Train | Test | Train | Test | |
NHV | 51 | 51 | 58 | 58 | 41 | 41 |
Rice | 84 | 83 | 100 | 99 | 86 | 85 |
Bare soil | 19 | 19 | 20 | 19 | 19 | 19 |
Water areas | 28 | 27 | 24 | 25 | 28 | 27 |
Trees | 27 | 27 | 26 | 26 | 27 | 27 |
Total | 209 | 207 | 228 | 227 | 201 | 199 |
Predictor | Description | Time Horizon Application |
---|---|---|
Min | Minimum value | PTOT, P1, P2, P3 |
Max | Maximum value | PTOT, P1, P2, P3 |
Min_occur | Occurrence of the minimum value | PTOT, P1, P2, P3 |
Max_occur | Occurrence of the maximum value | PTOT, P1, P2, P3 |
Mean | Mean value | PTOT, P1, P2, P3 |
Sd | Standard deviation | PTOT, P1, P2, P3 |
Span | Difference between maximum and minimum values | PTOT, P1, P2, P3 |
Span_harv_dec | Difference between maximum value and value at the end of December | PTOT |
Span_harv_30 | Difference between maximum value and value after around 30 days | PTOT |
Span_harv_45 | Difference between maximum value and value after around 45 days | PTOT |
Year | Number of Selected Predictors | Number of Trees (ntrees) | Number of Predictors in the Random Subset (mtry) | OOB Error |
---|---|---|---|---|
2017 | 31 | 500 | 5 | 0.158 |
2018 | 29 | 500 | 4 | 0.154 |
2019 | 21 | 1500 | 4 | 0.114 |
Year | NHV | R | BS | W | T | Total | U_ACC | O_ACC | K_COEF | |
---|---|---|---|---|---|---|---|---|---|---|
2017 | NHV | 34 | 16 | 1 | 0 | 0 | 51 | 66.7 | ||
R | 9 | 72 | 0 | 0 | 2 | 83 | 86.7 | |||
BS | 0 | 1 | 16 | 2 | 0 | 19 | 84.2 | |||
W | 0 | 0 | 1 | 26 | 0 | 27 | 96.3 | |||
T | 0 | 0 | 0 | 0 | 27 | 27 | 1 | |||
Total | 43 | 89 | 18 | 28 | 29 | 207 | ||||
P_ACC | 79.1 | 80.9 | 88.9 | 92.9 | 93.1 | |||||
O_ACC | 84.5 | |||||||||
K_COEF | 0.681 | |||||||||
2018 | NHV | 40 | 17 | 0 | 0 | 1 | 58 | 69 | ||
R | 11 | 86 | 0 | 0 | 2 | 99 | 86.9 | |||
BS | 0 | 0 | 17 | 2 | 0 | 19 | 89.5 | |||
W | 0 | 0 | 0 | 25 | 0 | 25 | 1 | |||
T | 0 | 1 | 0 | 0 | 25 | 26 | 96.2 | |||
Total | 51 | 104 | 17 | 27 | 28 | 227 | ||||
P_ACC | 78.4 | 82.7 | 1 | 92.6 | 89.3 | |||||
O_ACC | 85 | |||||||||
K_COEF | 0.686 | |||||||||
2019 | NHV | 27 | 13 | 0 | 0 | 1 | 41 | 65.9 | ||
R | 5 | 76 | 0 | 0 | 4 | 85 | 89.4 | |||
BS | 0 | 0 | 19 | 0 | 0 | 19 | 1 | |||
W | 1 | 0 | 1 | 25 | 0 | 27 | 92.6 | |||
T | 0 | 0 | 0 | 0 | 27 | 27 | 1 | |||
Total | 33 | 89 | 20 | 25 | 32 | 199 | ||||
P_ACC | 81.8 | 85.4 | 95 | 1 | 84.4 | |||||
O_ACC | 87.4 | |||||||||
K_COEF | 0.798 |
Dataset | 2017 | 2018 | 2019 | ||||||
---|---|---|---|---|---|---|---|---|---|
OA | RUA | RPA | OA | RUA | RPA | OA | RUA | RPA | |
S1 | 73.4 | 76.7 | 70.6 | 72.3 | 81.2 | 71.7 | 77.4 | 80 | 78.1 |
S2 | 75.4 | 79.7 | 76.6 | 76.7 | 83.9 | 79.4 | 79.9 | 86.3 | 80 |
S1+S2 | 84.5 | 86.7 | 80.9 | 85 | 86.9 | 82.7 | 87.4 | 89.4 | 85.4 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Fiorillo, E.; Di Giuseppe, E.; Fontanelli, G.; Maselli, F. Lowland Rice Mapping in Sédhiou Region (Senegal) Using Sentinel 1 and Sentinel 2 Data and Random Forest. Remote Sens. 2020, 12, 3403. https://doi.org/10.3390/rs12203403
Fiorillo E, Di Giuseppe E, Fontanelli G, Maselli F. Lowland Rice Mapping in Sédhiou Region (Senegal) Using Sentinel 1 and Sentinel 2 Data and Random Forest. Remote Sensing. 2020; 12(20):3403. https://doi.org/10.3390/rs12203403
Chicago/Turabian StyleFiorillo, Edoardo, Edmondo Di Giuseppe, Giacomo Fontanelli, and Fabio Maselli. 2020. "Lowland Rice Mapping in Sédhiou Region (Senegal) Using Sentinel 1 and Sentinel 2 Data and Random Forest" Remote Sensing 12, no. 20: 3403. https://doi.org/10.3390/rs12203403