Integration of multimodal data for large-scale rapid agricultural land evaluation using machine learning and deep learning approaches
Rapid and accurate agricultural land evaluation provides essential guidance for the supervision and allocation of agricultural land resources; it also helps to ensure food security. Previous work has mainly evaluated the land quality at the county level by using field sampling data and based on a fa...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-11-01
|
| Series: | Geoderma |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0016706123003737 |
| _version_ | 1797634022358122496 |
|---|---|
| author | Liangdan Li Luo Liu Yiping Peng Yingyue Su Yueming Hu Runyan Zou |
| author_facet | Liangdan Li Luo Liu Yiping Peng Yingyue Su Yueming Hu Runyan Zou |
| author_sort | Liangdan Li |
| collection | DOAJ |
| description | Rapid and accurate agricultural land evaluation provides essential guidance for the supervision and allocation of agricultural land resources; it also helps to ensure food security. Previous work has mainly evaluated the land quality at the county level by using field sampling data and based on a factor approach. However, it is difficult to achieve uniform, large-scale agricultural land evaluation via conventional approaches because of its spatial heterogeneity, as well as the large temporal and economic costs associated with data acquisition. In this study, we integrated publicly available multimodal data (i.e., satellite remote sensing, environmental, and socioeconomic data) into the Google Earth Engine (GEE) platform, selected the best indicators from each modality using the geodetector, on the basis of which different combinations of input models were designed. And then we developed machine learning (random forest, RF) and deep learning (deep neural network, DNN) models to evaluate the land quality in paddy field and dry land systems in 2013 throughout Guangdong Province, China. The results showed that the performance of our combination of variables decreased in the following order: multimodal > bimodal > unimodal. With the best input combination, the RF model (R2 = 0.91, RMSE = 97.56, and CCC = 0.95) outperformed the DNN model (R2 = 0.89, RMSE = 108.72, and CCC = 0.94) in terms of predicting the quality of paddy field. The RF model (R2 = 0.90, RMSE = 104.27, and CCC = 0.95) also outperformed the DNN model (R2 = 0.86, RMSE = 124.38, and CCC = 0.93) in terms of predicting the quality of dry land. The agricultural land quality estimates obtained using the RF and DNN models were more accurate for paddy field than for dry land systems because of greater land quality homogeneity in paddy fields. This research proposed a simple, low-cost for rapid and accurate agricultural land evaluation at the provincial scale using publicly available multimodal data, which can help to achieve control of the agricultural land grade at multiple spatial and temporal scales. |
| first_indexed | 2024-03-11T12:01:57Z |
| format | Article |
| id | doaj.art-b173fc4a72284ef6acb85822f7bd3129 |
| institution | Directory Open Access Journal |
| issn | 1872-6259 |
| language | English |
| last_indexed | 2024-03-11T12:01:57Z |
| publishDate | 2023-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Geoderma |
| spelling | doaj.art-b173fc4a72284ef6acb85822f7bd31292023-11-08T04:08:48ZengElsevierGeoderma1872-62592023-11-01439116696Integration of multimodal data for large-scale rapid agricultural land evaluation using machine learning and deep learning approachesLiangdan Li0Luo Liu1Yiping Peng2Yingyue Su3Yueming Hu4Runyan Zou5Guangdong Provincial Key Laboratory of Land Use and Consolidation, South China Agricultural University, Guangzhou 510642, China; Panyu Urban Planning & Survey Design Institute Limited Company, Guangzhou 511450, ChinaGuangdong Provincial Key Laboratory of Land Use and Consolidation, South China Agricultural University, Guangzhou 510642, China; Corresponding authors at: Guangdong Provincial Key Laboratory of Land Use and Consolidation, South China Agricultural University, Guangzhou 510642, China (L. Liu), Key Laboratory for Monitoring Tropical and Subtropical Natural Resources in South China, Ministry of Natural Resources, Guangzhou 510700, China (Y. Hu).Guangdong Provincial Key Laboratory of Land Use and Consolidation, South China Agricultural University, Guangzhou 510642, ChinaGuangdong Provincial Key Laboratory of Land Use and Consolidation, South China Agricultural University, Guangzhou 510642, ChinaKey Laboratory for Monitoring Tropical and Subtropical Natural Resources in South China, Ministry of Natural Resources, Guangzhou 510700, China; School of Tropical Agriculture and Forestry, Hainan University, Haikou 570228, China; Corresponding authors at: Guangdong Provincial Key Laboratory of Land Use and Consolidation, South China Agricultural University, Guangzhou 510642, China (L. Liu), Key Laboratory for Monitoring Tropical and Subtropical Natural Resources in South China, Ministry of Natural Resources, Guangzhou 510700, China (Y. Hu).Guangdong Provincial Key Laboratory of Land Use and Consolidation, South China Agricultural University, Guangzhou 510642, China; South China Academy of Natural Resources Science and Technology, Guangzhou 510642, ChinaRapid and accurate agricultural land evaluation provides essential guidance for the supervision and allocation of agricultural land resources; it also helps to ensure food security. Previous work has mainly evaluated the land quality at the county level by using field sampling data and based on a factor approach. However, it is difficult to achieve uniform, large-scale agricultural land evaluation via conventional approaches because of its spatial heterogeneity, as well as the large temporal and economic costs associated with data acquisition. In this study, we integrated publicly available multimodal data (i.e., satellite remote sensing, environmental, and socioeconomic data) into the Google Earth Engine (GEE) platform, selected the best indicators from each modality using the geodetector, on the basis of which different combinations of input models were designed. And then we developed machine learning (random forest, RF) and deep learning (deep neural network, DNN) models to evaluate the land quality in paddy field and dry land systems in 2013 throughout Guangdong Province, China. The results showed that the performance of our combination of variables decreased in the following order: multimodal > bimodal > unimodal. With the best input combination, the RF model (R2 = 0.91, RMSE = 97.56, and CCC = 0.95) outperformed the DNN model (R2 = 0.89, RMSE = 108.72, and CCC = 0.94) in terms of predicting the quality of paddy field. The RF model (R2 = 0.90, RMSE = 104.27, and CCC = 0.95) also outperformed the DNN model (R2 = 0.86, RMSE = 124.38, and CCC = 0.93) in terms of predicting the quality of dry land. The agricultural land quality estimates obtained using the RF and DNN models were more accurate for paddy field than for dry land systems because of greater land quality homogeneity in paddy fields. This research proposed a simple, low-cost for rapid and accurate agricultural land evaluation at the provincial scale using publicly available multimodal data, which can help to achieve control of the agricultural land grade at multiple spatial and temporal scales.http://www.sciencedirect.com/science/article/pii/S0016706123003737Agricultural land evaluationMultimodal dataGoogle Earth EngineGeodetectorMachine learningDeep learning |
| spellingShingle | Liangdan Li Luo Liu Yiping Peng Yingyue Su Yueming Hu Runyan Zou Integration of multimodal data for large-scale rapid agricultural land evaluation using machine learning and deep learning approaches Geoderma Agricultural land evaluation Multimodal data Google Earth Engine Geodetector Machine learning Deep learning |
| title | Integration of multimodal data for large-scale rapid agricultural land evaluation using machine learning and deep learning approaches |
| title_full | Integration of multimodal data for large-scale rapid agricultural land evaluation using machine learning and deep learning approaches |
| title_fullStr | Integration of multimodal data for large-scale rapid agricultural land evaluation using machine learning and deep learning approaches |
| title_full_unstemmed | Integration of multimodal data for large-scale rapid agricultural land evaluation using machine learning and deep learning approaches |
| title_short | Integration of multimodal data for large-scale rapid agricultural land evaluation using machine learning and deep learning approaches |
| title_sort | integration of multimodal data for large scale rapid agricultural land evaluation using machine learning and deep learning approaches |
| topic | Agricultural land evaluation Multimodal data Google Earth Engine Geodetector Machine learning Deep learning |
| url | http://www.sciencedirect.com/science/article/pii/S0016706123003737 |
| work_keys_str_mv | AT liangdanli integrationofmultimodaldataforlargescalerapidagriculturallandevaluationusingmachinelearninganddeeplearningapproaches AT luoliu integrationofmultimodaldataforlargescalerapidagriculturallandevaluationusingmachinelearninganddeeplearningapproaches AT yipingpeng integrationofmultimodaldataforlargescalerapidagriculturallandevaluationusingmachinelearninganddeeplearningapproaches AT yingyuesu integrationofmultimodaldataforlargescalerapidagriculturallandevaluationusingmachinelearninganddeeplearningapproaches AT yueminghu integrationofmultimodaldataforlargescalerapidagriculturallandevaluationusingmachinelearninganddeeplearningapproaches AT runyanzou integrationofmultimodaldataforlargescalerapidagriculturallandevaluationusingmachinelearninganddeeplearningapproaches |