Yield prediction is of great significance for yield mapping, crop market planning, crop insurance, and harvest management. Remote sensing is becoming increasingly important in crop yield prediction. Based on remote sensing data, great progress has been made in this field by using machine learning, especially the Deep Learning (DL) method, including Convolutional Neural Network (CNN) or Long Short-Term Memory (LSTM). Recent experiments in this area suggested that CNN can explore more spatial features and LSTM has the ability to reveal phenological characteristics, which both play an important role in crop yield prediction. However, very few experiments combining these two models for crop yield prediction have been reported. In this paper, we propose a deep CNN-LSTM model for both end-of-season and in-season soybean yield prediction in CONUS at the county-level. The model was trained by crop growth variables and environment variables, which include weather data, MODIS Land Surface Temperature (LST) data, and MODIS Surface Reflectance (SR) data; historical soybean yield data were employed as labels. Based on the Google Earth Engine (GEE), all these training data were combined and transformed into histogram-based tensors for deep learning. The results of the experiment indicate that the prediction performance of the proposed CNN-LSTM model can outperform the pure CNN or LSTM model in both end-of-season and in-season. The proposed method shows great potential in improving the accuracy of yield prediction for other crops like corn, wheat, and potatoes at fine scales in the future.

Accurate and timely estimation of crop yield at a small scale is of great significance to food security and harvest management. Recent studies have proven remote sensing is an efficient method for yield estimation and machine learning, especially deep learning, can infer a good prediction by integrating multi-source datasets like satellite data, climate data, soil data, and so on. However, there are some bottleneck challenges to improve accuracy. First, the popular remote sensing data used for yield prediction fall into two major groups, time-series data, and constant data. Surprisingly little attention has been devoted to deep learning networks that can integrate the two kinds of data effectively; second, both temporal and spatial features play a role in affecting the yields. But most of the existing approaches employed either CNN (convolutional neural network) or RNN (recurrent neural network). CNN cannot learn temporal patterns, while RNN barely can learn spatial characteristics. This work proposed a novel multi-level deep learning (MLDL) model coupling RNN and CNN to extract both spatial and temporal features. The inputs include both time-series remote sensing data and soil property data and the model outputs yield. We experimented with the model in U.S. Corn Belt states and used it to predict corn yield from 2013 to 2016 at the county-level. The results approve the effectiveness and advantages of the proposed approach over the other methods. In the future, the model will be used on other crops like soybean and winter wheat to assist agriculture decision making.

The knowledge of the area and spatial distribution of paddy rice fields is important for water resource management. However, accurate map of paddy rice is a long-term challenge because of its spatiotemporal discontinuity and short duration. To solve this problem, this study proposed a paddy rice area extraction approach by using the combination of optical vegetation indices and synthetic aperture radar (SAR) data. This method is designed to overcome the data-missing problem due to cloud contamination and spatiotemporal discontinuities of the traditional optical remote sensing method. More specifically, the Sentinel-1A SAR and the Sentinel-2 multispectral imager (MSI) Level-2A imagery are used to identify paddy rice with a high temporal and spatial resolution. Three vegetation indices, namely normalized difference vegetation index (NDVI), enhanced vegetation index (EVI), and land surface water index (LSWI), are estimated from optical bands. Two polarization bands (VH (vertical-horizontal) and VV (vertical-vertical)) are used to overcome the cloud contamination problem. This approach was applied with the random forest machine learning algorithm on the Google Earth Engine platform for the Jianghan Plain in China as an experimental area. The results of 39 experiments uncovered the effect of different factors. The results indicated that the combination of VV and VH band showed a better performance compared with other polarization bands; the average producer’s accuracy of paddy rice (PA) is 72.79%, 1.58% higher than the second one VH. Secondly, the combination of three indices also showed a better result than others, with average PA 73.82%, 1.42% higher than using NDVI alone. The classification result presented the best combination is EVI, VV, and VH polarization band. The producer’s accuracy of paddy rice was 76.67%, with the overall accuracy (OA) of 66.07%, and Kappa statistics of 0.45. However, NDVI, EVI, and VH showed better performance in mapping the morphology. The results demonstrated the method developed in this study can be successfully applied to the cloud-prone area for mapping paddy rice to overcome the data missing caused by cloud and rain during the paddy growing season.

Due to the increasing demand for the monitoring of crop conditions and food production, it is a challenging and meaningful task to identify crops from remote sensing images. The state-of the-art crop classification models are mostly built on supervised classification models such as support vector machines (SVM), convolutional neural networks (CNN), and long- and short-term memory neural networks (LSTM). Meanwhile, as an unsupervised generative model, the adversarial generative network (GAN) is rarely used to complete classification tasks for agricultural applications. In this work, we propose a new method that combines GAN, CNN, and LSTM models to classify crops of corn and soybeans from remote sensing time-series images, in which GAN’s discriminator was used as the final classifier. The method is feasible on the condition that the training samples are small, and it fully takes advantage of spectral, spatial, and phenology features of crops from satellite data. The classification experiments were conducted on crops of corn, soybeans, and others. To verify the effectiveness of the proposed method, comparisons with models of SVM, SegNet, CNN, LSTM, and different combinations were also conducted. The results show that our method achieved the best classification results, with the Kappa coefficient of 0.7933 and overall accuracy of 0.86. Experiments in other study areas also demonstrate the extensibility of the proposed method.

During the last few decades, worsening air quality has been diagnosed in many cities around the world. The accurately prediction of air pollutants, particularly, particulate matter 2.5 (PM2.5) is extremely important for environmental management. A Convolutional Neural Network (CNN) P-CNN model is presented in this paper, which uses seven different pollutant satellite images, such as Aerosol index (AER AI), Methane (CH₄), Carbon monoxide (CO), Formaldehyde (HCHO), Nitrogen dioxide (NO₂), Ozone (O₃) and Sulfur dioxide (SO₂), as auxiliary variables to estimate daily average PM2.5 concentrations. This study estimates daily average of PM2.5 concentrations in various cities of Pakistan (Islamabad, Lahore, Peshawar and Karachi) by using satellite images. The dataset contains a total of 2562 images from May-2019 to April-2020. We compare and analyze AlexNet, VGG16, ResNet50 and P-CNN model on every dataset. The accuracy of machine learning models was checked with Mean Absolute Error (MAE), Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). The results show that P-CNN is more accurate than other approaches in estimating PM2.5 concentrations from satellite images. This study presents robust model using satellite images, useful for estimating PM2.5 concentrations.