A landscape metrics-based sample weighting approach for forecasting land cover change with deep learning models

References

• Abrams M, Tsu H, Hulley G, Iwao K, Pieri D, Cudahy T, Kargel J. 2015. The advanced spaceborne thermal emission and reflection radiometer (ASTER) after fifteen years: review of global products. Int J Appl Earth Observ Geoinf. 38:292–301. doi: 10.1016/j.jag.2015.01.013.
   Web of Science ®Google Scholar
• Aguejdad R, Houet T, Hubert-Moy L. 2017. Spatial validation of land use change models using multiple assessment techniques: a case study of transition potential models. Environ Model Assess. 22(6):591–606. doi: 10.1007/s10666-017-9564-4.
   Web of Science ®Google Scholar
• Ahmadlou M, Karimi M, Pontius RG. 2022. A new framework to deal with the class imbalance problem in urban gain modeling based on clustering and ensemble models. Geocarto Int. 37(19):5669–5692. doi: 10.1080/10106049.2021.1923826.
   Web of Science ®Google Scholar
• Ahmed B, Ahmed R, Zhu X. 2013. Evaluation of model validation techniques in land cover dynamics. IJGI. 2(3):577–597. doi: 10.3390/ijgi2030577.
   Google Scholar
• Amiri BJ, Asgarian A, Sakieh Y. 2017. Introducing landscape accuracy metric for spatial performance evaluation of land use/land cover change models. Geocarto Int. 32(11):1171–1187. doi: 10.1080/10106049.2016.1206628.
   Web of Science ®Google Scholar
• Arevalo P, Stanimirova R, Bullock E, Zhang Y, Tarrio K, Turlej K, Hu K, et al. 2022. Global land cover mapping and estimation yearly 30 m V001. Distributed by NASA EOSDIS Land Processes DAAC. 2022. doi: 10.5067/MEaSUREs/GLanCE/GLanCE30.001.
   Google Scholar
• Asempah M, Sahwan W, Schütt B. 2021. Assessment of land cover dynamics and drivers of urban expansion using geospatial and logistic regression approach in WA Municipality, Ghana. Land. 10(11):1251. doi: 10.3390/land10111251.
   Web of Science ®Google Scholar
• Brandt J, Stolle F. 2021. A global method to identify trees outside of closed-canopy forests with medium-resolution satellite imagery. Int J Remote Sens. 42(5):1713–1737. doi: 10.1080/01431161.2020.1841324.
   Web of Science ®Google Scholar
• Broeck WAVd, Goedemé T, Loopmans M. 2022. Multiclass land cover mapping from historical orthophotos using domain adaptation and spatio-temporal transfer learning. Remote Sens. 14(23):5911. doi: 10.3390/rs14235911.
   Google Scholar
• Cao C, Dragićević S, Li S. 2019. Short-term forecasting of land use change using recurrent neural network models. Sustainability (Switzerland). 11(19):5376. doi: 10.3390/su11195376.
   Web of Science ®Google Scholar
• Cho K, van Merrienboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y. 2014. Learning phrase representations using RNN encoder–decoder for statistical machine translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 1724–34. Stroudsburg, PA, USA: Association for Computational Linguistics. doi: 10.3115/v1/D14-1179.
   Google Scholar
• Chollet F. 2015. Keras: the Python Deep Learning Library. Keras.Io. Astrophysics source code library. 2015. https://keras.io/.
   Google Scholar
• Cui Y, Jia M, Lin TY, Song Y, Belongie S. 2019. Class-balanced loss based on effective number of samples. In. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2019-June, 9260–9269. doi: 10.1109/CVPR.2019.00949.
   Google Scholar
• Esri. 2023. Train Deep Learning Model (Image Analyst). ArcGIS Pro 3.1 Tool Reference. 2023. https://pro.arcgis.com/en/pro-app/latest/tool-reference/image-analyst/train-deep-learning-model.htm.
   Google Scholar
• Foody GM. 2020. Explaining the unsuitability of the Kappa Coefficient in the assessment and comparison of the accuracy of thematic maps obtained by image classification. Remote Sens Environ. 239(March):111630. doi: 10.1016/j.rse.2019.111630.
   Google Scholar
• Fotheringham AS, Rogerson PA. 1993. GIS and spatial analytical problems. Int J Geogr Inf Syst. 7(1):3–19. doi: 10.1080/02693799308901936.
   Google Scholar
• Frazier AE, Kedron P. 2017. Landscape metrics: past progress and future directions. Curr Landsc Ecol Rep. 2(3):63–72. doi: 10.1007/s40823-017-0026-0.
   Google Scholar
• Friedl MA, Woodcock CE, Olofsson P, Zhu Z, Loveland T, Stanimirova R, Arevalo P, Bullock E, Hu K-T, Zhang Y, et al. 2022. Medium spatial resolution mapping of global land cover and land cover change across multiple decades from landsat. Front Remote Sens. 3:0–15. doi: 10.3389/frsen.2022.894571.
   Google Scholar
• Ghemawat S, Zheng X, Moore S, Abadi M, Dean J, Chen Z, Kudlur M, et al. 2016. TensorFlow: a system for large-scale machine learning. In Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2016, p. 265–83.
   Google Scholar
• Gordon-Rodriguez E, Loaiza-Ganem G, Pleiss G, Cunningham JP. 2020. Uses and abuses of the cross-entropy loss: case studies in modern deep learning. In Proceedings on “I Can’t Believe It’s Not Better!” at NeurIPS Workshops, PMLR 137, p. 1–10.
   Google Scholar
• Griffith JA. 2004. The role of landscape pattern analysis in understanding concepts of land cover change. J Geogr Sci. 14(S1):3–17. doi: 10.1007/BF02873085.
   Google Scholar
• Guo Y, Zhang S, Yang J, Yu G, Wang Y. 2022. Dual memory scale network for multi-step time series forecasting in thermal environment of aquaculture facility: a case study of recirculating aquaculture water temperature. Expert Syst Appl. 208(May 2021):118218. doi: 10.1016/j.eswa.2022.118218.
   Google Scholar
• Halseth G, Markey S, Ryser L, Hanlon N, Skinner M. 2017. Exploring new development pathways in a remote mining town: the case of Tumbler Ridge, BC Canada. J Rural Community Dev. 12(2–3):1–22.
   Google Scholar
• Harati S, Perez L, Molowny-Horas R. 2020. Integrating neighborhood effect and supervised machine learning techniques to model and simulate forest insect outbreaks in British Columbia, Canada. Forests. 11(11):1215. doi: 10.3390/f11111215.
   Web of Science ®Google Scholar
• He H, Garcia EA. 2009. Learning from imbalanced data. IEEE Trans Knowl Data Eng 21(9): 1263–1284. doi: 10.1109/TKDE.2008.239.
   Web of Science ®Google Scholar
• Hesselbarth MH, Sciaini M, With KA, Wiegand K, Nowosad J. 2019. Landscapemetrics: an open-source r tool to calculate landscape metrics. Ecography. 42(10):1648–1657. doi: 10.1111/ecog.04617.
   Web of Science ®Google Scholar
• Hewage P, Behera A, Trovati M, Pereira E, Ghahremani M, Palmieri F, Liu Y. 2020. Temporal convolutional neural (TCN) network for an effective weather forecasting using time-series data from the local weather station. Soft Comput. 24(21):16453–16482. doi: 10.1007/s00500-020-04954-0.
   Web of Science ®Google Scholar
• Hochreiter S, Schmidhuber J. 1997. Long short-term memory. Neural Comput. 9(8):1735–1780. doi: 10.1162/neco.1997.9.8.1735.
   PubMed Web of Science ®Google Scholar
• Jagannathan J, Divya C. 2021. Deep learning for the prediction and classification of land use and land cover changes using deep convolutional neural network. Ecol Inform 65:101412. doi: 10.1016/j.ecoinf.2021.101412.
   Web of Science ®Google Scholar
• Johnson JM, Khoshgoftaar TM. 2019. Survey on deep learning with class imbalance. J Big Data. 6:27. doi: 10.1186/s40537-019-0192-5.
   PubMedGoogle Scholar
• Kang M, Liu Y, Wang M, Li L, Weng M. 2022. A random forest classifier with cost-sensitive learning to extract urban landmarks from an imbalanced dataset. Int J Geogr Inf Sci. 36(3):496–513. doi: 10.1080/13658816.2021.1977814.
   Web of Science ®Google Scholar
• Karpatne A, Jiang Z, Vatsavai RR, Shekhar S, Kumar V. 2016. Monitoring land-cover changes: a machine-learning perspective. IEEE Geosci Remote Sens Mag. 4(2):8–21. doi: 10.1109/MGRS.2016.2528038.
   Web of Science ®Google Scholar
• Kellenberger B, Marcos D, Tuia D. 2018. Detecting mammals in UAV images: best practices to address a substantially imbalanced dataset with deep learning. Remote Sens Environ. 216:139–153. doi: 10.1016/j.rse.2018.06.028.
   Web of Science ®Google Scholar
• Lausch A, Herzog F. 2002. Applicability of landscape metrics for the monitoring of landscape change: issues of scale, resolution and interpretability. Ecol Indic. 2(1–2):3–15. doi: 10.1016/S1470-160X(02)00053-5.
   Google Scholar
• Lea C, Flynn MD, Vidal R, Reiter A, Hager GD. 2017. Temporal convolutional networks for action segmentation and detection. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, p. 1003–1012. Institute of Electrical and Electronics Engineers Inc. doi: 10.1109/CVPR.2017.113.
   Google Scholar
• LeCun Y, Bengio Y, Hinton G. 2015. Deep learning. Nature. 521(7553):436–444. doi: 10.1038/nature14539.
   PubMed Web of Science ®Google Scholar
• Li X, Yeh AG-O. 2002. Neural-network-based cellular automata for simulating multiple land use changes using GIS. Int J Geogr Inf Sci. 16(4):323–343. doi: 10.1080/13658810210137004.
   Web of Science ®Google Scholar
• Lin J, Li X, Wen Y, He P. 2023. Modeling urban land-use changes using a landscape-driven patch-based cellular automaton (LP-CA). Cities. 132:103906. doi: 10.1016/j.cities.2022.103906.
   Web of Science ®Google Scholar
• Lu J, Ren K, Li X, Zhao Y, Xu Z, Ren X. 2022. From reanalysis to satellite observations: gap-filling with imbalanced learning. GeoInformatica. 26(2):397–428. doi: 10.1007/s10707-020-00426-7.
   Web of Science ®Google Scholar
• Machemer P, Simmons C, Walker R. 2006. Refining landscape change models through outlier analysis in the Muskegon watershed of Michigan. Landsc Res. 31(3):277–294. doi: 10.1080/01426390600783426.
   Web of Science ®Google Scholar
• Martínez S, Mollicone D. 2012. From land cover to land use: a methodology to assess land use from remote sensing data. Remote Sens. 4(4):1024–1045. doi: 10.3390/rs4041024.
   Google Scholar
• Masolele RN, De Sy V, Herold M, Marcos D, Verbesselt J, Gieseke F, Mullissa AG, Martius C. 2021. Spatial and temporal deep learning methods for deriving land-use following deforestation: a pan-tropical case study using Landsat time series. Remote Sens Environ. 264:112600. doi: 10.1016/j.rse.2021.112600.
   Web of Science ®Google Scholar
• Mungai LM, Messina JP, Zulu LC, Qi J, Snapp S. 2022. Modeling spatiotemporal patterns of land use/land cover change in central Malawi using a neural network model. Remote Sens. 14(14):3477. doi: 10.3390/rs14143477.
   Google Scholar
• Naushad R, Kaur T, Ghaderpour E. 2021. Deep transfer learning for land use and land cover classification: a comparative study. Sensors. 21(23):8083. doi: 10.3390/s21238083.
   PubMed Web of Science ®Google Scholar
• Nguyen HM, Demir B, Dalponte M. 2019. A weighted SVM-based approach to tree species classification at individual tree crown level using LiDAR data. Remote Sens. 11(24):2948. doi: 10.3390/rs11242948.
   Google Scholar
• Nikparvar B, Thill J-C. 2021. Machine learning of spatial data. IJGI. 10(9):600. doi: 10.3390/ijgi10090600.
   Google Scholar
• Paegelow M, Camacho Olmedo MT, Mas J, Houet T. 2014. Benchmarking of LUCC modelling tools by various validation techniques and error analysis. Cybergeo: Eur J of Geogr. doi: 10.4000/cybergeo.26610.
   Google Scholar
• Parker DC, Manson SM, Janssen MA, Hoffmann MJ, Deadman P. 2003. Multi-agent systems for the simulation of land-use and land-cover change: a review. Ann Assoc Am Geogr. 93(2):314–337. doi: 10.1111/1467-8306.9302004.
   Web of Science ®Google Scholar
• Pedregosa F, Varoquaux G, Gramfort MBA, Michel V, Thirion B, Grisel O. 2011. Scikit-learn: machine learning in Python. J Mach Learn Res. 12:2825–2830. doi: 10.5555/1953048.2078195.
   Web of Science ®Google Scholar
• Pickard B, Gray J, Meentemeyer R. 2017. Comparing quantity, allocation and configuration accuracy of multiple land change models. Land. 6(3):52. doi: 10.3390/land6030052.
   Web of Science ®Google Scholar
• Plexida SG, Sfougaris AI, Ispikoudis IP, Papanastasis VP. 2014. Selecting landscape metrics as indicators of spatial heterogeneity-acomparison among Greek landscapes. Int J Appl Earth Observ Geoinf. 26(1):26–35. doi: 10.1016/j.jag.2013.05.001.
   Google Scholar
• Pontius RG, Boersma W, Castella J-C, Clarke K, de Nijs T, Dietzel C, Duan Z, Fotsing E, Goldstein N, Kok K, et al. 2008. Comparing the input, output, and validation maps for several models of land change. Ann Reg Sci. 42(1):11–37. doi: 10.1007/s00168-007-0138-2.
   Web of Science ®Google Scholar
• Remy P. 2020. Temporal convolutional networks for Keras. GitHub Repository. 2020. https://github.com/philipperemy/keras-tcn.
   Google Scholar
• Ren Y, Lü Y, Comber A, Fu B, Harris P, Wu L. 2019. Spatially explicit simulation of land use/land cover changes: current coverage and future prospects. Earth-Sci Rev. 190:398–415. doi: 10.1016/j.earscirev.2019.01.001.
   Web of Science ®Google Scholar
• Rossum G. V. 2009. Python language reference. Amsterdam, Netherlands: Python Software Foundation. doi: 10.1201/9781584889304.axd.
   Google Scholar
• Ryser L, Halseth G, Markey S, Gunton C, Argent N. 2019. Path dependency or investing in place: understanding the changing conditions for rural resource regions. Extr Ind Soc. 6(1):29–40. doi: 10.1016/j.exis.2018.10.009.
   Google Scholar
• Sefrin O, Riese FM, Keller S. 2020. Deep learning for land cover change detection. Remote Sens. 13(1):78. doi: 10.3390/rs13010078.
   Google Scholar
• Shi X, Chen Z, Wang H, Yeung D-Y, Wong W-K, Woo W-C. 2015. Convolutional LSTM Network: a machine learning approach for precipitation nowcasting. In Advances in Neural Information Processing Systems 28 (NIPS 2015), p. 802–810. doi: 10.1074/jbc.M200827200.
   Google Scholar
• Statistics Canada. 2023. Census Profile. 2021 Census of Population. Statistics Canada Catalogue No. 98-316-X2021001. https://www12.statcan.gc.ca/census-recensement/2021/dp-pd/prof/index.cfm?Lang=E.
   Google Scholar
• Sun P, Lu Y, Zhai J. 2022. Mapping land cover using a developed U-net model with weighted cross entropy. Geocarto Int. 37(25):9355–9368. doi: 10.1080/10106049.2021.2017017.
   Web of Science ®Google Scholar
• Tarawneh AS, Hassanat AB, Altarawneh GA, Almuhaimeed A. 2022. Stop oversampling for class imbalance learning: a review. IEEE Access. 10:47643–47660. doi: 10.1109/ACCESS.2022.3169512.
   Google Scholar
• Turner BL, Lambin EF, Reenberg A. 2007. The emergence of land change science for global environmental change and sustainability. Proc Natl Acad Sci USA. 104(52):20666–20671. doi: 10.1073/pnas.0704119104.
   PubMed Web of Science ®Google Scholar
• van Duynhoven A, Dragićević S. 2019. Analyzing the effects of temporal resolution and classification confidence for modeling land cover change with long short-term memory networks. Remote Sens. 11(23):2784. doi: 10.3390/rs11232784.
   Google Scholar
• van Duynhoven A, Dragićević S. 2022a. Assessing the impact of neighborhood size on temporal convolutional networks for modeling land cover change. Remote Sens. 14(19):4957. doi: 10.3390/rs14194957.
   Google Scholar
• van Duynhoven A, Dragićević S. 2022b. Mitigating imbalance of land cover change data for deep learning models with temporal and spatiotemporal sample weighting schemes. IJGI. 11(12):587. doi: 10.3390/ijgi11120587.
   Google Scholar
• Varga OG, Pontius RG, Jr, Szabó Z, Szabó S. 2020. Effects of category aggregation on land change simulation based on Corine land cover data. Remote Sens. 12(8):1314. doi: 10.3390/rs12081314.
   Google Scholar
• Wang J, Bretz M, Ali Akber Dewan M, Delavar MA. 2022. Machine learning in modelling land-use and land cover-change (LULCC): current status, challenges and prospects. Sci Total Environ. 822:153559. doi: 10.1016/j.scitotenv.2022.153559.
   PubMed Web of Science ®Google Scholar
• Wang H, Zhao X, Zhang X, Wu D, Du X. 2019. Long time series land cover classification in China from 1982 to 2015 based on Bi-LSTM deep learning. Remote Sens. 11(14):1639. doi: 10.3390/rs11141639.
   Google Scholar
• Wu J. 2004. Effects of changing scale on landscape pattern analysis: scaling relations. Landsc Ecol. 19(2):125–138. doi: 10.1023/B:LAND.0000021711.40074.ae.
   Web of Science ®Google Scholar
• Xiao C, Chen N, Hu C, Wang K, Xu Z, Cai Y, Xu L, Chen Z, Gong J. 2019. A spatiotemporal deep learning model for sea surface temperature field prediction using time-series satellite data. Environ Modell Softw. 120:104502. doi: 10.1016/j.envsoft.2019.104502.
   Web of Science ®Google Scholar
• Xiao B, Liu J, Jiao J, Li Y, Liu X, Zhu W. 2022. Modeling dynamic land use changes in the eastern portion of the Hexi Corridor, China by Cnn-Gru hybrid model. GISci Remote Sens. 59(1):501–519. doi: 10.1080/15481603.2022.2037888.
   Web of Science ®Google Scholar
• Xing W, Qian Y, Guan X, Yang T, Wu H. 2020. A novel cellular automata model integrated with deep learning for dynamic spatio-temporal land use change simulation. Comput Geosci. 137:104430. doi: 10.1016/j.cageo.2020.104430.
   Web of Science ®Google Scholar
• Yaghoobi M, Vafaeenejad A, Moradi H, Hashemi H. 2022. Analysis of landscape composition and configuration based on LULC change modeling. Sustainability (Switzerland). 14(20):13070. doi: 10.3390/su142013070.
   Web of Science ®Google Scholar
• Yan K, Hu Q, Wang H, Huang X, Li L, Ji S. 2022. Continuous mapping convolution for large-scale point clouds semantic segmentation. IEEE Geosci Remote Sensing Lett. 19:1–5. doi: 10.1109/LGRS.2021.3107006.
   Web of Science ®Google Scholar
• Yang X, Qi Zheng X, Chen R. 2014. A land use change model: integrating landscape pattern indexes and Markov-CA. Ecol Modell. 283:1–7. doi: 10.1016/j.ecolmodel.2014.03.011.
   Web of Science ®Google Scholar
• Ye L, Gao L, Marcos-Martinez R, Mallants D, Bryan BA. 2019. Projecting Australia’s Forest Cover dynamics and exploring influential factors using deep learning. Environ Modell Softw. 119(September):407–417. doi: 10.1016/j.envsoft.2019.07.013.
   Google Scholar
• Zhang C, Li X. 2022. Land use and land cover mapping in the era of big data. Land. 11(10):1692. doi: 10.3390/land11101692.
   Web of Science ®Google Scholar
• Zhang T, Liu J, Wang J. 2022. Rainstorm prediction via a deep spatio-temporal-attributed affinity network. Geocarto Int. 37(26):13079–13097. doi: 10.1080/10106049.2022.2076914.
   Web of Science ®Google Scholar
• Zhang H, Song Y, Xu S, He Y, Li Z, Yu X, Liang Y, Wu W, Wang Y. 2022. Combining a class-weighted algorithm and machine learning models in landslide susceptibility mapping: a case study of Wanzhou section of the three gorges reservoir, China. Comput Geosci. 158:104966. doi: 10.1016/j.cageo.2021.104966.
   Web of Science ®Google Scholar
• Zhang X, Zhou Y, Luo J. 2022. Deep learning for processing and analysis of remote sensing big data: a technical review. Big Earth Data. 6(4):527–560. doi: 10.1080/20964471.2021.1964879.
   Google Scholar
• Zhong L, Hu L, Zhou H. 2019. Deep learning based multi-temporal crop classification. Remote Sens Environ. 221:430–443. doi: 10.1016/j.rse.2018.11.032.
   Web of Science ®Google Scholar
• Zhu R, Janowicz K, Mai G. 2019. Making direction a first-class citizen of Tobler’s First Law of Geography. Trans GIS. 23(3):398–416. doi: 10.1111/tgis.12550.
   Web of Science ®Google Scholar
• Zhu Z, Qiu S, Ye S. 2022. Remote sensing of land change: a multifaceted perspective. Remote Sens Environ. 282:113266. doi: 10.1016/j.rse.2022.113266.
   Web of Science ®Google Scholar