Recently, replacing chemical fertilizers with straw returning and new fertilizers has received considerable attention in the agricultural sector, as it is believed to increase rice yield and improve soil properties. However, less is known about rice growth and soil properties in paddy fields with the addition of different fertilizers. Thus, in this paper, we investigated the effects of different fertilizer treatments, including no fertilization (CK), optimized fertilization based on the medium yield recommended fertilizer amount (OF), 4.50 Mg ha⁻¹ straw returning with chemical fertilizers (SF), 0.59 Mg ha⁻¹ slow-release fertilizer with chemical fertilizers (SRF), and 0.60 Mg ha⁻¹ water-soluble fertilizer with chemical fertilizers (WSF), on rice growth, yield, and soil properties through a field experiment. The results show that compared with the OF treatment, the new SF, SRF, and WSF treatments increased plant height, main root length, tiller number, leaf area index, chlorophyll content, and aboveground dry weight. The SF, SRF, and WSF treatments improved rice grain yield by 30.65–32.51% and 0.24–1.66% compared to the CK and OF treatments, respectively. The SRF treatment increased nitrogen (N) and phosphorus (P) uptake by 18.78% and 28.68%, the harvest indexes of N and P by 1.75% and 0.59%, and the partial productivity of N and P by 2.64% and 2.63%, respectively, compared with the OF treatment. However, fertilization did not significantly affect the average yield, harvest indexes of N and P, and partial productivity of N and P. The contents of TN, AN, SOM, TP, AP, and AK across all the treatments decreased significantly with increasing soil depth, while soil pH increased with soil depth. The SF treatment could more effectively increase soil pH and NH₄⁺-N content compared to the SRF and WSF treatments, while the SRF treatment could greatly enhance other soil nutrients and enzyme activities compared to the SF and WSF treatments. A correlation analysis showed that rice yield was significantly positively associated with tiller number, leaf area index, chlorophyll, soil NO₃⁻-N, NH₄⁺-N, SOM, TP, AK, and soil enzyme activity. The experimental results indicate that SRF was the best fertilization method to improve rice growth and yield and enhance soil properties, followed by the SF, WSF, and OF treatments. Hence, the results provide useful information for better fertilization management in the Chaohu Lake region of China.

Timely and accurate extraction of crop planting structure information is of great importance for food security and sustainable agricultural development. However, long time series data with high spatial resolution have a much larger data volume, which seriously limits the quality and efficiency of the application of remote sensing to agriculture in complex crop rotation areas. To address this problem, this paper takes Lujiang County, a typical complex crop rotation region in the middle and lower reaches of the Yangtze River in China as an example, and proposes utilizing the Google Earth Engine (GEE) platform to extract the Normalized Difference Vegetation Index (NDVI), Normalized Difference Yellowness Index (NDYI) and Vertical-Horizontal Polarization (VH) time series sets of the whole planting year, and combining the Simple Non-Iterative Clustering (SNIC) multi-scale segmentation with the Support Vector Machine (SVM) and Random Forest (RF) algorithms to realize the fast and high-quality planting information of the main crop rotation patterns in the complex rotation region. The results show that by combining time series and object-oriented methods, SVM leads to better improvement than RF, with its overall accuracy and Kappa coefficient increasing by 4.44% and 0.0612, respectively, but RF is more suitable for extracting the planting structure in complex crop rotation areas. The RF algorithm combined with time series object-oriented extraction (OB + T + RF) achieved the highest accuracy, with an overall accuracy and Kappa coefficient of 98.93% and 0.9854, respectively. When compared to the pixel-oriented approach combined with the Support Vector Machine algorithm based on multi-temporal data (PB + M + SVM), the proposed method effectively reduces the presence of salt-and-pepper noise in the results, resulting in an improvement of 6.14% in overall accuracy and 0.0846 in Kappa coefficient. The research results can provide a new idea and a reliable reference method for obtaining crop planting structure information efficiently and accurately in complex crop rotation areas.